drm next/fixes for 5.16-rc1

bridge: - HPD improvments for lt9611uxc - eDP aux-bus support for ps8640 - LVDS data-mapping selection support ttm: - remove huge page functionality (needs reworking) - fix a race condition during BO eviction panels: - add some new panels fbdev: - fix double-free - remove unused scrolling acceleration - CONFIG_FB dep improvements locking: - improve contended locking logging - naming collision fix dma-buf: - add dma_resv_for_each_fence iterator - fix fence refcounting bug - name locking fixesA prime: - fix object references during mmap nouveau: - various code style changes - refcount fix - device removal fixes - protect client list with a mutex - fix CE0 address calculation i915: - DP rates related fixes - Revert disabling dual eDP that was causing state readout problems - put the cdclk vtables in const data - Fix DVO port type for older platforms - Fix blankscreen by turning DP++ TMDS output buffers on encoder->shutdown - CCS FBs related fixes - Fix recursive lock in GuC submission - Revert guc_id from i915_request tracepoint - Build fix around dmabuf amdgpu: - GPU reset fix - Aldebaran fix - Yellow Carp fixes - DCN2.1 DMCUB fix - IOMMU regression fix for Picasso - DSC display fixes - BPC display calculation fixes - Other misc display fixes - Don't allow partial copy from user for DC debugfs - SRIOV fixes - GFX9 CSB pin count fix - Various IP version check fixes - DP 2.0 fixes - Limit DCN1 MPO fix to DCN1 amdkfd: - SVM fixes - Fix gfx version for renoir - Reset fixes udl: - timeout fix imx: - circular locking fix virtio: - NULL ptr deref fix -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEEKbZHaGwW9KfbeusDHTzWXnEhr4FAmGN3YwACgkQDHTzWXnE hr6aZQ/+Pobf1VE7V3wPUcopxccJYmgBvG/uY8EDyjA8qaxHs2pQqGN2IooOGxr6 F8G1N94Hem/PCDn3T8JI2Tqw5z4sy4UwLahEWISurFCen1IMAfA7hYfutp9X3O7X 8h7b+PgkvVruEAHF7z0kqnWGPHmcro29cIHNkXVRjnJuz+Gmn1XRfo6Jj65n6D7u NfMeU4/lWRR3767oJQzTqyAYtGxsKaZT3/tBD5WggZBzEKC7hqhAl8EUoOLWwojo fDqwiEpLXpraPRIQH8trkXVHhzPeLAmG916WwS8JG3CEk9mUQ+I7Jshhd8cw+bsQ XPuk3OBfU9mtuiGgNzrLP3xXJZs/QN3EkpKZWLefTnJY+C4BgiP2RifTnghmwV31 6/7Pr83CX/cn3BRd7r0xaeBZYvVYBZmwoZcsZFJBM8SVjd/ofKUfAmCzZZKheio2 5qa6bj9DQoyjEoFAULh23plcX6hvATGP7wzfRTnJ9AlAJ0KyEjVJ3r0qE6jHMDc/ uzcTAnKIWCxt9kSgE5qwLQtxLBaBpr/iOniZbCqGkPjiZeMzqP/ug1AKVP7kk39x FxZVT8ZOKk8Xt4iLZx8jmHi2KKheXYZi9LqieoTrJd44qMXDOmR9DCtQX9FZuWJS EJAlMj6sCowAZdODPZMVpoMc3Gti9nZ2Fpu7mLrRcMk1gKfjKwo= =qMNk -----END PGP SIGNATURE----- Merge tag 'drm-next-2021-11-12' of git://anongit.freedesktop.org/drm/drm Pull more drm updates from Dave Airlie: "I missed a drm-misc-next pull for the main pull last week. It wasn't that major and isn't the bulk of this at all. This has a bunch of fixes all over, a lot for amdgpu and i915. bridge: - HPD improvments for lt9611uxc - eDP aux-bus support for ps8640 - LVDS data-mapping selection support ttm: - remove huge page functionality (needs reworking) - fix a race condition during BO eviction panels: - add some new panels fbdev: - fix double-free - remove unused scrolling acceleration - CONFIG_FB dep improvements locking: - improve contended locking logging - naming collision fix dma-buf: - add dma_resv_for_each_fence iterator - fix fence refcounting bug - name locking fixesA prime: - fix object references during mmap nouveau: - various code style changes - refcount fix - device removal fixes - protect client list with a mutex - fix CE0 address calculation i915: - DP rates related fixes - Revert disabling dual eDP that was causing state readout problems - put the cdclk vtables in const data - Fix DVO port type for older platforms - Fix blankscreen by turning DP++ TMDS output buffers on encoder->shutdown - CCS FBs related fixes - Fix recursive lock in GuC submission - Revert guc_id from i915_request tracepoint - Build fix around dmabuf amdgpu: - GPU reset fix - Aldebaran fix - Yellow Carp fixes - DCN2.1 DMCUB fix - IOMMU regression fix for Picasso - DSC display fixes - BPC display calculation fixes - Other misc display fixes - Don't allow partial copy from user for DC debugfs - SRIOV fixes - GFX9 CSB pin count fix - Various IP version check fixes - DP 2.0 fixes - Limit DCN1 MPO fix to DCN1 amdkfd: - SVM fixes - Fix gfx version for renoir - Reset fixes udl: - timeout fix imx: - circular locking fix virtio: - NULL ptr deref fix" * tag 'drm-next-2021-11-12' of git://anongit.freedesktop.org/drm/drm: (126 commits) drm/ttm: Double check mem_type of BO while eviction drm/amdgpu: add missed support for UVD IP_VERSION(3, 0, 64) drm/amdgpu: drop jpeg IP initialization in SRIOV case drm/amd/display: reject both non-zero src_x and src_y only for DCN1x drm/amd/display: Add callbacks for DMUB HPD IRQ notifications drm/amd/display: Don't lock connection_mutex for DMUB HPD drm/amd/display: Add comment where CONFIG_DRM_AMD_DC_DCN macro ends drm/amdkfd: Fix retry fault drain race conditions drm/amdkfd: lower the VAs base offset to 8KB drm/amd/display: fix exit from amdgpu_dm_atomic_check() abruptly drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov drm/amdgpu: fix uvd crash on Polaris12 during driver unloading drm/i915/adlp/fb: Prevent the mapping of redundant trailing padding NULL pages drm/i915/fb: Fix rounding error in subsampled plane size calculation drm/i915/hdmi: Turn DP++ TMDS output buffers back on in encoder->shutdown() drm/locking: fix __stack_depot_* name conflict drm/virtio: Fix NULL dereference error in virtio_gpu_poll drm/amdgpu: fix SI handling in amdgpu_device_asic_has_dc_support() drm/amdgpu: Fix dangling kfd_bo pointer for shared BOs drm/amd/amdkfd: Don't sent command to HWS on kfd reset ...
2024-12-04 03:14:02 +08:00 · 2021-11-12 12:11:07 -08:00 · 2021-11-12 12:11:07 -08:00 · 304ac8032d
commit 304ac8032d
parent f78e9de80f b6c2472524
140 changed files with 1770 additions and 1501 deletions
--- a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
@ -49,11 +49,26 @@ properties:

    properties:
      port@0:
-        $ref: /schemas/graph.yaml#/properties/port
+        $ref: /schemas/graph.yaml#/$defs/port-base
        description: |
          For LVDS encoders, port 0 is the parallel input
          For LVDS decoders, port 0 is the LVDS input

+        properties:
+          endpoint:
+            $ref: /schemas/media/video-interfaces.yaml#
+            unevaluatedProperties: false
+
+            properties:
+              data-mapping:
+                enum:
+                  - jeida-18
+                  - jeida-24
+                  - vesa-24
+                description: |
+                  The color signals mapping order. See details in
+                  Documentation/devicetree/bindings/display/panel/lvds.yaml
+
      port@1:
        $ref: /schemas/graph.yaml#/properties/port
        description: |
@ -71,6 +86,22 @@ properties:

  power-supply: true

+if:
+  not:
+    properties:
+      compatible:
+        contains:
+          const: lvds-decoder
+then:
+  properties:
+    ports:
+      properties:
+        port@0:
+          properties:
+            endpoint:
+              properties:
+                data-mapping: false
+
 required:
  - compatible
  - ports
--- a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
@ -40,6 +40,9 @@ properties:
  vdd33-supply:
    description: Regulator for 3.3V digital core power.

+  aux-bus:
+    $ref: /schemas/display/dp-aux-bus.yaml#
+
  ports:
    $ref: /schemas/graph.yaml#/properties/ports

@ -98,7 +101,21 @@ examples:
                    reg = <1>;
                    ps8640_out: endpoint {
                        remote-endpoint = <&panel_in>;
-                   };
+                    };
+                };
+            };
+
+            aux-bus {
+                panel {
+                    compatible = "boe,nv133fhm-n62";
+                    power-supply = <&pp3300_dx_edp>;
+                    backlight = <&backlight>;
+
+                    port {
+                        panel_in: endpoint {
+                            remote-endpoint = <&ps8640_out>;
+                        };
+                    };
                };
            };
        };
--- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
@ -166,6 +166,8 @@ properties:
      - innolux,at070tn92
        # Innolux G070Y2-L01 7" WVGA (800x480) TFT LCD panel
      - innolux,g070y2-l01
+        # Innolux G070Y2-T02 7" WVGA (800x480) TFT LCD TTL panel
+      - innolux,g070y2-t02
        # Innolux Corporation 10.1" G101ICE-L01 WXGA (1280x800) LVDS panel
      - innolux,g101ice-l01
        # Innolux Corporation 12.1" WXGA (1280x800) TFT LCD panel
@ -309,6 +311,8 @@ properties:
      - urt,umsh-8596md-11t
      - urt,umsh-8596md-19t
      - urt,umsh-8596md-20t
+        # Vivax TPC-9150 tablet 9.0" WSVGA TFT LCD panel
+      - vivax,tpc9150-panel
        # VXT 800x480 color TFT LCD panel
      - vxt,vl050-8048nt-c01
        # Winstar Display Corporation 3.5" QVGA (320x240) TFT LCD panel
@ -317,6 +321,7 @@ properties:
      - yes-optoelectronics,ytc700tlag-05-201c

  backlight: true
+  ddc-i2c-bus: true
  enable-gpios: true
  port: true
  power-supply: true
--- a/Documentation/devicetree/bindings/display/panel/sharp,ls060t1sx01.yaml
+++ b/Documentation/devicetree/bindings/display/panel/sharp,ls060t1sx01.yaml
@ -0,0 +1,56 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/sharp,ls060t1sx01.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sharp Microelectronics 6.0" FullHD TFT LCD panel
+
+maintainers:
+  - Dmitry Baryskov <dmitry.baryshkov@linaro.org>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: sharp,ls060t1sx01
+
+  reg: true
+  backlight: true
+  reset-gpios: true
+  port: true
+
+  avdd-supply:
+    description: handle of the regulator that provides the positive supply voltage
+  avee-supply:
+    description: handle of the regulator that provides the negative supply voltage
+  vddi-supply:
+    description: handle of the regulator that provides the I/O supply voltage
+  vddh-supply:
+    description: handle of the regulator that provides the analog supply voltage
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    dsi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        panel@0 {
+            compatible = "sharp,ls060t1sx01";
+            reg = <0>;
+            avdd-supply = <&pm8941_l22>;
+            backlight = <&backlight>;
+            reset-gpios = <&pm8916_gpios 25 GPIO_ACTIVE_LOW>;
+        };
+    };
+
+...
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@ -1286,6 +1286,8 @@ patternProperties:
    description: Vitesse Semiconductor Corporation
  "^vivante,.*":
    description: Vivante Corporation
+  "^vivax,.*":
+    description: Vivax brand by M SAN Grupa d.o.o.
  "^vocore,.*":
    description: VoCore Studio
  "^voipac,.*":
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@ -314,16 +314,19 @@ Level: Advanced
 Garbage collect fbdev scrolling acceleration
 --------------------------------------------

-Scroll acceleration is disabled in fbcon by hard-wiring p->scrollmode =
-SCROLL_REDRAW. There's a ton of code this will allow us to remove:
+Scroll acceleration has been disabled in fbcon. Now it works as the old
+SCROLL_REDRAW mode. A ton of code was removed in fbcon.c and the hook bmove was
+removed from fbcon_ops.
+Remaining tasks:

- lots of code in fbcon.c
-
- a bunch of the hooks in fbcon_ops, maybe the remaining hooks could be called
+- a bunch of the hooks in fbcon_ops could be removed or simplified by calling
  directly instead of the function table (with a switch on p->rotate)

 - fb_copyarea is unused after this, and can be deleted from all drivers

+- after that, fb_copyarea can be deleted from fb_ops in include/linux/fb.h as
+  well as cfb_copyarea
+
 Note that not all acceleration code can be deleted, since clearing and cursor
 support is still accelerated, which might be good candidates for further
 deletion projects.
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@ -67,12 +67,9 @@ static void dma_buf_release(struct dentry *dentry)
 	BUG_ON(dmabuf->vmapping_counter);

 	/*
-	 * Any fences that a dma-buf poll can wait on should be signaled
-	 * before releasing dma-buf. This is the responsibility of each
-	 * driver that uses the reservation objects.
-	 *
-	 * If you hit this BUG() it means someone dropped their ref to the
-	 * dma-buf while still having pending operation to the buffer.
+	 * If you hit this BUG() it could mean:
+	 * * There's a file reference imbalance in dma_buf_poll / dma_buf_poll_cb or somewhere else
+	 * * dmabuf->cb_in/out.active are non-0 despite no pending fence callback
 	 */
 	BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active);

@ -200,6 +197,7 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence)
 static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
 	struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb;
+	struct dma_buf *dmabuf = container_of(dcb->poll, struct dma_buf, poll);
 	unsigned long flags;

 	spin_lock_irqsave(&dcb->poll->lock, flags);
@ -207,21 +205,18 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 	dcb->active = 0;
 	spin_unlock_irqrestore(&dcb->poll->lock, flags);
 	dma_fence_put(fence);
+	/* Paired with get_file in dma_buf_poll */
+	fput(dmabuf->file);
 }

-static bool dma_buf_poll_shared(struct dma_resv *resv,
+static bool dma_buf_poll_add_cb(struct dma_resv *resv, bool write,
 				struct dma_buf_poll_cb_t *dcb)
 {
-	struct dma_resv_list *fobj = dma_resv_shared_list(resv);
+	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
-	int i, r;
+	int r;

-	if (!fobj)
-		return false;
-
-	for (i = 0; i < fobj->shared_count; ++i) {
-		fence = rcu_dereference_protected(fobj->shared[i],
-						  dma_resv_held(resv));
+	dma_resv_for_each_fence(&cursor, resv, write, fence) {
 		dma_fence_get(fence);
 		r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb);
 		if (!r)
@ -232,24 +227,6 @@ static bool dma_buf_poll_shared(struct dma_resv *resv,
 	return false;
 }

-static bool dma_buf_poll_excl(struct dma_resv *resv,
-			      struct dma_buf_poll_cb_t *dcb)
-{
-	struct dma_fence *fence = dma_resv_excl_fence(resv);
-	int r;
-
-	if (!fence)
-		return false;
-
-	dma_fence_get(fence);
-	r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb);
-	if (!r)
-		return true;
-	dma_fence_put(fence);
-
-	return false;
-}
-
 static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 {
 	struct dma_buf *dmabuf;
@ -282,8 +259,10 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 		spin_unlock_irq(&dmabuf->poll.lock);

 		if (events & EPOLLOUT) {
-			if (!dma_buf_poll_shared(resv, dcb) &&
-			    !dma_buf_poll_excl(resv, dcb))
+			/* Paired with fput in dma_buf_poll_cb */
+			get_file(dmabuf->file);
+
+			if (!dma_buf_poll_add_cb(resv, true, dcb))
 				/* No callback queued, wake up any other waiters */
 				dma_buf_poll_cb(NULL, &dcb->cb);
 			else
@ -303,7 +282,10 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 		spin_unlock_irq(&dmabuf->poll.lock);

 		if (events & EPOLLIN) {
-			if (!dma_buf_poll_excl(resv, dcb))
+			/* Paired with fput in dma_buf_poll_cb */
+			get_file(dmabuf->file);
+
+			if (!dma_buf_poll_add_cb(resv, false, dcb))
 				/* No callback queued, wake up any other waiters */
 				dma_buf_poll_cb(NULL, &dcb->cb);
 			else
@ -1356,10 +1338,9 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 {
 	struct dma_buf *buf_obj;
 	struct dma_buf_attachment *attach_obj;
-	struct dma_resv *robj;
-	struct dma_resv_list *fobj;
+	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
-	int count = 0, attach_count, shared_count, i;
+	int count = 0, attach_count;
 	size_t size = 0;
 	int ret;

@ -1378,6 +1359,8 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 		if (ret)
 			goto error_unlock;

+
+		spin_lock(&buf_obj->name_lock);
 		seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n",
 				buf_obj->size,
 				buf_obj->file->f_flags, buf_obj->file->f_mode,
@ -1385,22 +1368,12 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 				buf_obj->exp_name,
 				file_inode(buf_obj->file)->i_ino,
 				buf_obj->name ?: "");
+		spin_unlock(&buf_obj->name_lock);

-		robj = buf_obj->resv;
-		fence = dma_resv_excl_fence(robj);
-		if (fence)
-			seq_printf(s, "\tExclusive fence: %s %s %ssignalled\n",
-				   fence->ops->get_driver_name(fence),
-				   fence->ops->get_timeline_name(fence),
-				   dma_fence_is_signaled(fence) ? "" : "un");
-
-		fobj = rcu_dereference_protected(robj->fence,
-						 dma_resv_held(robj));
-		shared_count = fobj ? fobj->shared_count : 0;
-		for (i = 0; i < shared_count; i++) {
-			fence = rcu_dereference_protected(fobj->shared[i],
-							  dma_resv_held(robj));
-			seq_printf(s, "\tShared fence: %s %s %ssignalled\n",
+		dma_resv_for_each_fence(&cursor, buf_obj->resv, true, fence) {
+			seq_printf(s, "\t%s fence: %s %s %ssignalled\n",
+				   dma_resv_iter_is_exclusive(&cursor) ?
+					"Exclusive" : "Shared",
 				   fence->ops->get_driver_name(fence),
 				   fence->ops->get_timeline_name(fence),
 				   dma_fence_is_signaled(fence) ? "" : "un");
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@ -333,10 +333,14 @@ static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor)
 {
 	cursor->seq = read_seqcount_begin(&cursor->obj->seq);
 	cursor->index = -1;
-	if (cursor->all_fences)
+	cursor->shared_count = 0;
+	if (cursor->all_fences) {
 		cursor->fences = dma_resv_shared_list(cursor->obj);
-	else
+		if (cursor->fences)
+			cursor->shared_count = cursor->fences->shared_count;
+	} else {
 		cursor->fences = NULL;
+	}
 	cursor->is_restarted = true;
 }

@ -363,7 +367,7 @@ static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor)
 				continue;

 		} else if (!cursor->fences ||
-			   cursor->index >= cursor->fences->shared_count) {
+			   cursor->index >= cursor->shared_count) {
 			cursor->fence = NULL;
 			break;

@ -423,6 +427,57 @@ struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor)
 }
 EXPORT_SYMBOL(dma_resv_iter_next_unlocked);

+/**
+ * dma_resv_iter_first - first fence from a locked dma_resv object
+ * @cursor: cursor to record the current position
+ *
+ * Return the first fence in the dma_resv object while holding the
+ * &dma_resv.lock.
+ */
+struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor)
+{
+	struct dma_fence *fence;
+
+	dma_resv_assert_held(cursor->obj);
+
+	cursor->index = 0;
+	if (cursor->all_fences)
+		cursor->fences = dma_resv_shared_list(cursor->obj);
+	else
+		cursor->fences = NULL;
+
+	fence = dma_resv_excl_fence(cursor->obj);
+	if (!fence)
+		fence = dma_resv_iter_next(cursor);
+
+	cursor->is_restarted = true;
+	return fence;
+}
+EXPORT_SYMBOL_GPL(dma_resv_iter_first);
+
+/**
+ * dma_resv_iter_next - next fence from a locked dma_resv object
+ * @cursor: cursor to record the current position
+ *
+ * Return the next fences from the dma_resv object while holding the
+ * &dma_resv.lock.
+ */
+struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor)
+{
+	unsigned int idx;
+
+	dma_resv_assert_held(cursor->obj);
+
+	cursor->is_restarted = false;
+	if (!cursor->fences || cursor->index >= cursor->fences->shared_count)
+		return NULL;
+
+	idx = cursor->index++;
+	return rcu_dereference_protected(cursor->fences->shared[idx],
+					 dma_resv_held(cursor->obj));
+}
+EXPORT_SYMBOL_GPL(dma_resv_iter_next);
+
 /**
 * dma_resv_copy_fences - Copy all fences from src to dst.
 * @dst: the destination reservation object
@ -448,10 +503,8 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)
 			dma_resv_list_free(list);
 			dma_fence_put(excl);

-			if (cursor.fences) {
-				unsigned int cnt = cursor.fences->shared_count;
-
-				list = dma_resv_list_alloc(cnt);
+			if (cursor.shared_count) {
+				list = dma_resv_list_alloc(cursor.shared_count);
 				if (!list) {
 					dma_resv_iter_end(&cursor);
 					return -ENOMEM;
@ -522,7 +575,7 @@ int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl,
 			if (fence_excl)
 				dma_fence_put(*fence_excl);

-			count = cursor.fences ? cursor.fences->shared_count : 0;
+			count = cursor.shared_count;
 			count += fence_excl ? 0 : 1;

 			/* Eventually re-allocate the array */
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@ -100,11 +100,25 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS
          This has the potential to use a lot of memory and print some very
          large kernel messages. If in doubt, say "N".

+config DRM_DEBUG_MODESET_LOCK
+	bool "Enable backtrace history for lock contention"
+	depends on STACKTRACE_SUPPORT
+	depends on DEBUG_KERNEL
+	depends on EXPERT
+	select STACKDEPOT
+	default y if DEBUG_WW_MUTEX_SLOWPATH
+	help
+	  Enable debug tracing of failures to gracefully handle drm modeset lock
+	  contention. A history of each drm modeset lock path hitting -EDEADLK
+	  will be saved until gracefully handled, and the backtrace will be
+	  printed when attempting to lock a contended lock.
+
+	  If in doubt, say "N".
+
 config DRM_FBDEV_EMULATION
 	bool "Enable legacy fbdev support for your modesetting driver"
-	depends on DRM
-	depends on FB=y || FB=DRM
-	select DRM_KMS_HELPER
+	depends on DRM_KMS_HELPER
+	depends on FB=y || FB=DRM_KMS_HELPER
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@ -297,7 +297,7 @@ void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd);
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm);
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo);
 void amdgpu_amdkfd_reserve_system_mem(uint64_t size);
 #else
 static inline
@ -312,7 +312,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 }

 static inline
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
 {
 }
 #endif
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@ -207,7 +207,7 @@ static void unreserve_mem_limit(struct amdgpu_device *adev,
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 }

-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	u32 domain = bo->preferred_domains;
@ -219,6 +219,8 @@ void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
 	}

 	unreserve_mem_limit(adev, amdgpu_bo_size(bo), domain, sg);
+
+	kfree(bo->kfd_bo);
 }


@ -734,14 +736,19 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 		}

 		/* Add BO to VM internal data structures */
+		ret = amdgpu_bo_reserve(bo[i], false);
+		if (ret) {
+			pr_debug("Unable to reserve BO during memory attach");
+			goto unwind;
+		}
 		attachment[i]->bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+		amdgpu_bo_unreserve(bo[i]);
 		if (unlikely(!attachment[i]->bo_va)) {
 			ret = -ENOMEM;
 			pr_err("Failed to add BO object to VM. ret == %d\n",
 			       ret);
 			goto unwind;
 		}
-
 		attachment[i]->va = va;
 		attachment[i]->pte_flags = get_pte_flags(adev, mem);
 		attachment[i]->adev = adev;
@ -757,7 +764,9 @@ unwind:
 		if (!attachment[i])
 			continue;
 		if (attachment[i]->bo_va) {
+			amdgpu_bo_reserve(bo[i], true);
 			amdgpu_vm_bo_rmv(adev, attachment[i]->bo_va);
+			amdgpu_bo_unreserve(bo[i]);
 			list_del(&attachment[i]->list);
 		}
 		if (bo[i])
@ -1568,12 +1577,12 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va,
 		mem->va + bo_size * (1 + mem->aql_queue));

-	ret = unreserve_bo_and_vms(&ctx, false, false);
-
 	/* Remove from VM internal data structures */
 	list_for_each_entry_safe(entry, tmp, &mem->attachments, list)
 		kfd_mem_detach(entry);

+	ret = unreserve_bo_and_vms(&ctx, false, false);
+
 	/* Free the sync object */
 	amdgpu_sync_free(&mem->sync);

@ -1600,9 +1609,13 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	drm_vma_node_revoke(&mem->bo->tbo.base.vma_node, drm_priv);
 	if (mem->dmabuf)
 		dma_buf_put(mem->dmabuf);
-	drm_gem_object_put(&mem->bo->tbo.base);
 	mutex_destroy(&mem->lock);
-	kfree(mem);
+
+	/* If this releases the last reference, it will end up calling
+	 * amdgpu_amdkfd_release_notify and kfree the mem struct. That's why
+	 * this needs to be the last call here.
+	 */
+	drm_gem_object_put(&mem->bo->tbo.base);

 	return ret;
 }
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@ -2398,10 +2398,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);

-	r = amdgpu_amdkfd_resume_iommu(adev);
-	if (r)
-		goto init_failed;
-
 	amdgpu_fru_get_product_info(adev);

 init_failed:
@ -3171,11 +3167,21 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
 #if defined(CONFIG_DRM_AMD_DC)
-#if defined(CONFIG_DRM_AMD_DC_SI)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
+		/*
+		 * We have systems in the wild with these ASICs that require
+		 * LVDS and VGA support which is not supported with DC.
+		 *
+		 * Fallback to the non-DC driver here by default so as not to
+		 * cause regressions.
+		 */
+#if defined(CONFIG_DRM_AMD_DC_SI)
+		return amdgpu_dc > 0;
+#else
+		return false;
 #endif
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
@ -4287,8 +4293,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;

-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
@ -4850,6 +4854,9 @@ static void amdgpu_device_recheck_guilty_jobs(

 		/* clear job's guilty and depend the folowing step to decide the real one */
 		drm_sched_reset_karma(s_job);
+		/* for the real bad job, it will be resubmitted twice, adding a dma_fence_get
+		 * to make sure fence is balanced */
+		dma_fence_get(s_job->s_fence->parent);
 		drm_sched_resubmit_jobs_ext(&ring->sched, 1);

 		ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
@ -4885,6 +4892,7 @@ retry:

 		/* got the hw fence, signal finished fence */
 		atomic_dec(ring->sched.score);
+		dma_fence_put(s_job->s_fence->parent);
 		dma_fence_get(&s_job->s_fence->finished);
 		dma_fence_signal(&s_job->s_fence->finished);
 		dma_fence_put(&s_job->s_fence->finished);
@ -5020,8 +5028,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,

 		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);

-		if (!amdgpu_sriov_vf(tmp_adev))
-			amdgpu_amdkfd_pre_reset(tmp_adev);
+		amdgpu_amdkfd_pre_reset(tmp_adev);

 		/*
 		 * Mark these ASICs to be reseted as untracked first
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@ -867,7 +867,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 		case IP_VERSION(2, 0, 2):
 		case IP_VERSION(2, 2, 0):
 			amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
-			amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
+			if (!amdgpu_sriov_vf(adev))
+				amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 			break;
 		case IP_VERSION(2, 0, 3):
 			break;
@ -881,6 +882,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 			break;
 		case IP_VERSION(3, 0, 0):
 		case IP_VERSION(3, 0, 16):
+		case IP_VERSION(3, 0, 64):
 		case IP_VERSION(3, 1, 1):
 		case IP_VERSION(3, 0, 2):
 			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@ -60,9 +60,10 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
 			goto unlock;
 		}

-		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
-					       TTM_BO_VM_NUM_PREFAULT, 1);
-		drm_dev_exit(idx);
+		 ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+						TTM_BO_VM_NUM_PREFAULT);
+
+		 drm_dev_exit(idx);
 	} else {
 		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
 	}
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@ -1423,6 +1423,8 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 	struct drm_amdgpu_info_firmware fw_info;
 	struct drm_amdgpu_query_fw query_fw;
 	struct atom_context *ctx = adev->mode_info.atom_context;
+	uint8_t smu_minor, smu_debug;
+	uint16_t smu_major;
 	int ret, i;

 	static const char *ta_fw_name[TA_FW_TYPE_MAX_INDEX] = {
@ -1568,8 +1570,11 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
 	if (ret)
 		return ret;
-	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n",
-		   fw_info.feature, fw_info.ver);
+	smu_major = (fw_info.ver >> 16) & 0xffff;
+	smu_minor = (fw_info.ver >> 8) & 0xff;
+	smu_debug = (fw_info.ver >> 0) & 0xff;
+	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x (%d.%d.%d)\n",
+		   fw_info.feature, fw_info.ver, smu_major, smu_minor, smu_debug);

 	/* SDMA */
 	query_fw.fw_type = AMDGPU_INFO_FW_SDMA;
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@ -1274,7 +1274,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	abo = ttm_to_amdgpu_bo(bo);

 	if (abo->kfd_bo)
-		amdgpu_amdkfd_unreserve_memory_limit(abo);
+		amdgpu_amdkfd_release_notify(abo);

 	/* We only remove the fence if the resv has individualized. */
 	WARN_ON_ONCE(bo->type == ttm_bo_type_kernel
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@ -134,6 +134,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 			adev->vcn.indirect_sram = true;
 		break;
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 64):
 		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0))
 			fw_name = FIRMWARE_SIENNA_CICHLID;
 		else
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@ -806,9 +806,9 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
 		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
 			pcs_clear_status(adev,
 					 xgmi23_pcs_err_status_reg_aldebaran[i]);
-		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
+		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++)
 			pcs_clear_status(adev,
-					 xgmi23_pcs_err_status_reg_aldebaran[i]);
+					 xgmi3x16_pcs_err_status_reg_aldebaran[i]);
 		for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++)
 			pcs_clear_status(adev,
 					 walf_pcs_err_status_reg_aldebaran[i]);
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@ -8249,6 +8249,9 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 reg, data;
+
+	amdgpu_gfx_off_ctrl(adev, false);
+
 	/* not for *_SOC15 */
 	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
@ -8263,6 +8266,8 @@ static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
 	else
 		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }

 static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev,
@ -8316,11 +8321,8 @@ static void gfx_v10_cntl_power_gating(struct amdgpu_device *adev, bool enable)
 	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		switch (adev->ip_versions[GC_HWIP][0]) {
 		case IP_VERSION(10, 3, 1):
-			data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
-			WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
-			break;
 		case IP_VERSION(10, 3, 3):
-			data = 0x1388 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
+			data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
 			WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
 			break;
 		default:
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@ -3575,12 +3575,16 @@ static void gfx_v7_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 data;

+	amdgpu_gfx_off_ctrl(adev, false);
+
 	data = RREG32(mmRLC_SPM_VMID);

 	data &= ~RLC_SPM_VMID__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_VMID__RLC_SPM_VMID_MASK) << RLC_SPM_VMID__RLC_SPM_VMID__SHIFT;

 	WREG32(mmRLC_SPM_VMID, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }

 static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@ -5624,6 +5624,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 data;

+	amdgpu_gfx_off_ctrl(adev, false);
+
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(mmRLC_SPM_VMID);
 	else
@ -5636,6 +5638,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_NO_KIQ(mmRLC_SPM_VMID, data);
 	else
 		WREG32(mmRLC_SPM_VMID, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }

 static const struct amdgpu_rlc_funcs iceland_rlc_funcs = {
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@ -2462,7 +2462,9 @@ static int gfx_v9_0_sw_fini(void *handle)
 	amdgpu_gfx_kiq_fini(adev);

 	gfx_v9_0_mec_fini(adev);
-	amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj);
+	amdgpu_bo_free_kernel(&adev->gfx.rlc.clear_state_obj,
+				&adev->gfx.rlc.clear_state_gpu_addr,
+				(void **)&adev->gfx.rlc.cs_ptr);
 	if (adev->flags & AMD_IS_APU) {
 		amdgpu_bo_free_kernel(&adev->gfx.rlc.cp_table_obj,
 				&adev->gfx.rlc.cp_table_gpu_addr,
@ -5102,6 +5104,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 reg, data;

+	amdgpu_gfx_off_ctrl(adev, false);
+
 	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
@ -5115,6 +5119,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
 	else
 		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }

 static bool gfx_v9_0_check_rlcg_range(struct amdgpu_device *adev,
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@ -348,6 +348,10 @@ static void gfxhub_v1_0_gart_disable(struct amdgpu_device *adev)
 		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT0_CNTL,
 				    i * hub->ctx_distance, 0);

+	if (amdgpu_sriov_vf(adev))
+		/* Avoid write to GMC registers */
+		return;
+
 	/* Setup TLB control */
 	tmp = RREG32_SOC15(GC, 0, mmMC_VM_MX_L1_TLB_CNTL);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, 0);
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@ -54,15 +54,17 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		seg_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE_ALDE),
 			MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+		max_region =
+			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE, PF_MAX_REGION);
 	} else {
 		xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
 		seg_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE),
 			MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+		max_region =
+			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
 	}

-	max_region =
-		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);


 	switch (adev->asic_type) {
@ -89,9 +91,15 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
 			return -EINVAL;

-		adev->gmc.xgmi.physical_node_id =
-		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
-			      PF_LFB_REGION);
+		if (adev->asic_type == CHIP_ALDEBARAN) {
+			adev->gmc.xgmi.physical_node_id =
+				REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE,
+						PF_LFB_REGION);
+		} else {
+			adev->gmc.xgmi.physical_node_id =
+				REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
+						PF_LFB_REGION);
+		}

 		if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
 			return -EINVAL;
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@ -182,6 +182,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 {
 	switch (adev->ip_versions[UVD_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 64):
 		if (amdgpu_sriov_vf(adev)) {
 			if (encode)
 				*codecs = &sriov_sc_video_codecs_encode;
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@ -534,6 +534,19 @@ static int uvd_v6_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;

+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (RREG32(mmUVD_STATUS) != 0)
+		uvd_v6_0_stop(adev);
+
+	return 0;
+}
+
+static int uvd_v6_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
@ -558,17 +571,6 @@ static int uvd_v6_0_hw_fini(void *handle)
 						       AMD_CG_STATE_GATE);
 	}

-	if (RREG32(mmUVD_STATUS) != 0)
-		uvd_v6_0_stop(adev);
-
-	return 0;
-}
-
-static int uvd_v6_0_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
 	r = uvd_v6_0_hw_fini(adev);
 	if (r)
 		return r;
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@ -406,7 +406,7 @@ static const struct kfd_device_info aldebaran_device_info = {
 static const struct kfd_device_info renoir_device_info = {
 	.asic_family = CHIP_RENOIR,
 	.asic_name = "renoir",
-	.gfx_target_version = 90002,
+	.gfx_target_version = 90012,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@ -1430,7 +1430,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,

 	if (!dqm->sched_running)
 		return 0;
-	if (dqm->is_hws_hang)
+	if (dqm->is_hws_hang || dqm->is_resetting)
 		return -EIO;
 	if (!dqm->active_runlist)
 		return retval;
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@ -308,7 +308,7 @@
 * 16MB are reserved for kernel use (CWSR trap handler and kernel IB
 * for now).
 */
-#define SVM_USER_BASE 0x1000000ull
+#define SVM_USER_BASE (u64)(KFD_CWSR_TBA_TMA_SIZE + 2*PAGE_SIZE)
 #define SVM_CWSR_BASE (SVM_USER_BASE - KFD_CWSR_TBA_TMA_SIZE)
 #define SVM_IB_BASE   (SVM_CWSR_BASE - PAGE_SIZE)

--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@ -281,6 +281,19 @@ static unsigned long svm_migrate_successful_pages(struct migrate_vma *migrate)
 	return cpages;
 }

+static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate)
+{
+	unsigned long upages = 0;
+	unsigned long i;
+
+	for (i = 0; i < migrate->npages; i++) {
+		if (migrate->src[i] & MIGRATE_PFN_VALID &&
+		    !(migrate->src[i] & MIGRATE_PFN_MIGRATE))
+			upages++;
+	}
+	return upages;
+}
+
 static int
 svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
@ -632,10 +645,11 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 		       struct vm_area_struct *vma, uint64_t start, uint64_t end)
 {
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
+	unsigned long upages = npages;
+	unsigned long cpages = 0;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
 	struct migrate_vma migrate;
-	unsigned long cpages = 0;
 	dma_addr_t *scratch;
 	size_t size;
 	void *buf;
@ -669,6 +683,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	if (!cpages) {
 		pr_debug("failed collect migrate device pages [0x%lx 0x%lx]\n",
 			 prange->start, prange->last);
+		upages = svm_migrate_unsuccessful_pages(&migrate);
 		goto out_free;
 	}
 	if (cpages != npages)
@ -681,8 +696,9 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 				    scratch, npages);
 	migrate_vma_pages(&migrate);

-	pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
-		svm_migrate_successful_pages(&migrate), cpages, migrate.npages);
+	upages = svm_migrate_unsuccessful_pages(&migrate);
+	pr_debug("unsuccessful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
+		 upages, cpages, migrate.npages);

 	svm_migrate_copy_done(adev, mfence);
 	migrate_vma_finalize(&migrate);
@ -696,9 +712,9 @@ out:
 		if (pdd)
 			WRITE_ONCE(pdd->page_out, pdd->page_out + cpages);

-		return cpages;
+		return upages;
 	}
-	return r;
+	return r ? r : upages;
 }

 /**
@ -718,7 +734,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
 	unsigned long addr;
 	unsigned long start;
 	unsigned long end;
-	unsigned long cpages = 0;
+	unsigned long upages = 0;
 	long r = 0;

 	if (!prange->actual_loc) {
@ -754,12 +770,12 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
 			pr_debug("failed %ld to migrate\n", r);
 			break;
 		} else {
-			cpages += r;
+			upages += r;
 		}
 		addr = next;
 	}

-	if (cpages) {
+	if (!upages) {
 		svm_range_vram_node_free(prange);
 		prange->actual_loc = 0;
 	}
@ -782,7 +798,7 @@ static int
 svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 			 struct mm_struct *mm)
 {
-	int r;
+	int r, retries = 3;

 	/*
 	 * TODO: for both devices with PCIe large bar or on same xgmi hive, skip
@ -791,9 +807,14 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,

 	pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc);

-	r = svm_migrate_vram_to_ram(prange, mm);
-	if (r)
-		return r;
+	do {
+		r = svm_migrate_vram_to_ram(prange, mm);
+		if (r)
+			return r;
+	} while (prange->actual_loc && --retries);
+
+	if (prange->actual_loc)
+		return -EDEADLK;

 	return svm_migrate_ram_to_vram(prange, best_loc, mm);
 }
@ -838,6 +859,11 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf)
 		pr_debug("failed find process at fault address 0x%lx\n", addr);
 		return VM_FAULT_SIGBUS;
 	}
+	if (READ_ONCE(p->svms.faulting_task) == current) {
+		pr_debug("skipping ram migration\n");
+		kfd_unref_process(p);
+		return 0;
+	}
 	addr >>= PAGE_SHIFT;
 	pr_debug("CPU page fault svms 0x%p address 0x%lx\n", &p->svms, addr);

--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@ -766,8 +766,10 @@ struct svm_range_list {
 	struct list_head		deferred_range_list;
 	spinlock_t			deferred_list_lock;
 	atomic_t			evicted_ranges;
+	bool				drain_pagefaults;
 	struct delayed_work		restore_work;
 	DECLARE_BITMAP(bitmap_supported, MAX_GPU_INSTANCE);
+	struct task_struct 		*faulting_task;
 };

 /* Process data */
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@ -1715,7 +1715,11 @@ int kfd_process_evict_queues(struct kfd_process *p)

 		r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm,
 							    &pdd->qpd);
-		if (r) {
+		/* evict return -EIO if HWS is hang or asic is resetting, in this case
+		 * we would like to set all the queues to be in evicted state to prevent
+		 * them been add back since they actually not be saved right now.
+		 */
+		if (r && r != -EIO) {
 			pr_err("Failed to evict process queues\n");
 			goto fail;
 		}
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@ -1496,9 +1496,11 @@ static int svm_range_validate_and_map(struct mm_struct *mm,

 		next = min(vma->vm_end, end);
 		npages = (next - addr) >> PAGE_SHIFT;
+		WRITE_ONCE(p->svms.faulting_task, current);
 		r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
 					       addr, npages, &hmm_range,
 					       readonly, true, owner);
+		WRITE_ONCE(p->svms.faulting_task, NULL);
 		if (r) {
 			pr_debug("failed %d to get svm range pages\n", r);
 			goto unreserve_out;
@ -2000,20 +2002,28 @@ static void svm_range_deferred_list_work(struct work_struct *work)
 		pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange,
 			 prange->start, prange->last, prange->work_item.op);

-		/* Make sure no stale retry fault coming after range is freed */
-		if (prange->work_item.op == SVM_OP_UNMAP_RANGE)
-			svm_range_drain_retry_fault(prange->svms);
-
 		mm = prange->work_item.mm;
+retry:
 		mmap_write_lock(mm);
 		mutex_lock(&svms->lock);

-		/* Remove from deferred_list must be inside mmap write lock,
+		/* Checking for the need to drain retry faults must be in
+		 * mmap write lock to serialize with munmap notifiers.
+		 *
+		 * Remove from deferred_list must be inside mmap write lock,
 		 * otherwise, svm_range_list_lock_and_flush_work may hold mmap
 		 * write lock, and continue because deferred_list is empty, then
 		 * deferred_list handle is blocked by mmap write lock.
 		 */
 		spin_lock(&svms->deferred_list_lock);
+		if (unlikely(svms->drain_pagefaults)) {
+			svms->drain_pagefaults = false;
+			spin_unlock(&svms->deferred_list_lock);
+			mutex_unlock(&svms->lock);
+			mmap_write_unlock(mm);
+			svm_range_drain_retry_fault(svms);
+			goto retry;
+		}
 		list_del_init(&prange->deferred_list);
 		spin_unlock(&svms->deferred_list_lock);

@ -2046,6 +2056,12 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
 			struct mm_struct *mm, enum svm_work_list_ops op)
 {
 	spin_lock(&svms->deferred_list_lock);
+	/* Make sure pending page faults are drained in the deferred worker
+	 * before the range is freed to avoid straggler interrupts on
+	 * unmapped memory causing "phantom faults".
+	 */
+	if (op == SVM_OP_UNMAP_RANGE)
+		svms->drain_pagefaults = true;
 	/* if prange is on the deferred list */
 	if (!list_empty(&prange->deferred_list)) {
 		pr_debug("update exist prange 0x%p work op %d\n", prange, op);
@ -2261,7 +2277,7 @@ svm_range_from_addr(struct svm_range_list *svms, unsigned long addr,
 * migration if actual loc is not best location, then update GPU page table
 * mapping to the best location.
 *
- * If vm fault gpu is range preferred loc, the best_loc is preferred loc.
+ * If the preferred loc is accessible by faulting GPU, use preferred loc.
 * If vm fault gpu idx is on range ACCESSIBLE bitmap, best_loc is vm fault gpu
 * If vm fault gpu idx is on range ACCESSIBLE_IN_PLACE bitmap, then
 *    if range actual loc is cpu, best_loc is cpu
@ -2278,7 +2294,7 @@ svm_range_best_restore_location(struct svm_range *prange,
 				struct amdgpu_device *adev,
 				int32_t *gpuidx)
 {
-	struct amdgpu_device *bo_adev;
+	struct amdgpu_device *bo_adev, *preferred_adev;
 	struct kfd_process *p;
 	uint32_t gpuid;
 	int r;
@ -2291,8 +2307,16 @@ svm_range_best_restore_location(struct svm_range *prange,
 		return -1;
 	}

-	if (prange->preferred_loc == gpuid)
+	if (prange->preferred_loc == gpuid ||
+	    prange->preferred_loc == KFD_IOCTL_SVM_LOCATION_SYSMEM) {
 		return prange->preferred_loc;
+	} else if (prange->preferred_loc != KFD_IOCTL_SVM_LOCATION_UNDEFINED) {
+		preferred_adev = svm_range_get_adev_by_id(prange,
+							prange->preferred_loc);
+		if (amdgpu_xgmi_same_hive(adev, preferred_adev))
+			return prange->preferred_loc;
+		/* fall through */
+	}

 	if (test_bit(*gpuidx, prange->bitmap_access))
 		return gpuid;
@ -2313,7 +2337,8 @@ svm_range_best_restore_location(struct svm_range *prange,

 static int
 svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
-				unsigned long *start, unsigned long *last)
+			       unsigned long *start, unsigned long *last,
+			       bool *is_heap_stack)
 {
 	struct vm_area_struct *vma;
 	struct interval_tree_node *node;
@ -2324,6 +2349,12 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 		pr_debug("VMA does not exist in address [0x%llx]\n", addr);
 		return -EFAULT;
 	}
+
+	*is_heap_stack = (vma->vm_start <= vma->vm_mm->brk &&
+			  vma->vm_end >= vma->vm_mm->start_brk) ||
+			 (vma->vm_start <= vma->vm_mm->start_stack &&
+			  vma->vm_end >= vma->vm_mm->start_stack);
+
 	start_limit = max(vma->vm_start >> PAGE_SHIFT,
 		      (unsigned long)ALIGN_DOWN(addr, 2UL << 8));
 	end_limit = min(vma->vm_end >> PAGE_SHIFT,
@ -2353,9 +2384,9 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 	*start = start_limit;
 	*last = end_limit - 1;

-	pr_debug("vma start: 0x%lx start: 0x%lx vma end: 0x%lx last: 0x%lx\n",
-		  vma->vm_start >> PAGE_SHIFT, *start,
-		  vma->vm_end >> PAGE_SHIFT, *last);
+	pr_debug("vma [0x%lx 0x%lx] range [0x%lx 0x%lx] is_heap_stack %d\n",
+		 vma->vm_start >> PAGE_SHIFT, vma->vm_end >> PAGE_SHIFT,
+		 *start, *last, *is_heap_stack);

 	return 0;
 }
@ -2420,11 +2451,13 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev,
 	struct svm_range *prange = NULL;
 	unsigned long start, last;
 	uint32_t gpuid, gpuidx;
+	bool is_heap_stack;
 	uint64_t bo_s = 0;
 	uint64_t bo_l = 0;
 	int r;

-	if (svm_range_get_range_boundaries(p, addr, &start, &last))
+	if (svm_range_get_range_boundaries(p, addr, &start, &last,
+					   &is_heap_stack))
 		return NULL;

 	r = svm_range_check_vm(p, start, last, &bo_s, &bo_l);
@ -2451,6 +2484,9 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev,
 		return NULL;
 	}

+	if (is_heap_stack)
+		prange->preferred_loc = KFD_IOCTL_SVM_LOCATION_SYSMEM;
+
 	svm_range_add_to_svms(prange);
 	svm_range_add_notifier_locked(mm, prange);

@ -3076,6 +3112,8 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 		struct svm_range *prange =
 				list_first_entry(&svm_bo->range_list,
 						struct svm_range, svm_bo_list);
+		int retries = 3;
+
 		list_del_init(&prange->svm_bo_list);
 		spin_unlock(&svm_bo->list_lock);

@ -3083,7 +3121,11 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 			 prange->start, prange->last);

 		mutex_lock(&prange->migrate_mutex);
-		svm_migrate_vram_to_ram(prange, svm_bo->eviction_fence->mm);
+		do {
+			svm_migrate_vram_to_ram(prange,
+						svm_bo->eviction_fence->mm);
+		} while (prange->actual_loc && --retries);
+		WARN(prange->actual_loc, "Migration failed during eviction");

 		mutex_lock(&prange->lock);
 		prange->svm_bo = NULL;
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@ -217,6 +217,7 @@ static const struct drm_format_info *
 amd_get_format_info(const struct drm_mode_fb_cmd2 *cmd);

 static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector);
+static void handle_hpd_rx_irq(void *param);

 static bool
 is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state,
@ -619,7 +620,7 @@ static void dm_dcn_vertical_interrupt0_high_irq(void *interrupt_params)

 	amdgpu_dm_crtc_handle_crc_window_irq(&acrtc->base);
 }
-#endif
+#endif /* CONFIG_DRM_AMD_SECURE_DISPLAY */

 /**
 * dmub_aux_setconfig_reply_callback - Callback for AUX or SET_CONFIG command.
@ -669,10 +670,7 @@ void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *not
 		return;
 	}

-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-
 	link_index = notify->link_index;
-
 	link = adev->dm.dc->links[link_index];

 	drm_connector_list_iter_begin(dev, &iter);
@ -685,10 +683,13 @@ void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *not
 		}
 	}
 	drm_connector_list_iter_end(&iter);
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);

-	if (hpd_aconnector)
-		handle_hpd_irq_helper(hpd_aconnector);
+	if (hpd_aconnector) {
+		if (notify->type == DMUB_NOTIFICATION_HPD)
+			handle_hpd_irq_helper(hpd_aconnector);
+		else if (notify->type == DMUB_NOTIFICATION_HPD_IRQ)
+			handle_hpd_rx_irq(hpd_aconnector);
+	}
 }

 /**
@ -764,6 +765,10 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params)
 				DRM_ERROR("DM: notify type %d invalid!", notify.type);
 				continue;
 			}
+			if (!dm->dmub_callback[notify.type]) {
+				DRM_DEBUG_DRIVER("DMUB notification skipped, no handler: type=%d\n", notify.type);
+				continue;
+			}
 			if (dm->dmub_thread_offload[notify.type] == true) {
 				dmub_hpd_wrk = kzalloc(sizeof(*dmub_hpd_wrk), GFP_ATOMIC);
 				if (!dmub_hpd_wrk) {
@ -813,7 +818,7 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params)
 	if (count > DMUB_TRACE_MAX_READ)
 		DRM_DEBUG_DRIVER("Warning : count > DMUB_TRACE_MAX_READ");
 }
-#endif
+#endif /* CONFIG_DRM_AMD_DC_DCN */

 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
@ -1410,7 +1415,15 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		switch (adev->ip_versions[DCE_HWIP][0]) {
 		case IP_VERSION(2, 1, 0):
 			init_data.flags.gpu_vm_support = true;
-			init_data.flags.disable_dmcu = true;
+			switch (adev->dm.dmcub_fw_version) {
+			case 0: /* development */
+			case 0x1: /* linux-firmware.git hash 6d9f399 */
+			case 0x01000000: /* linux-firmware.git hash 9a0b0f4 */
+				init_data.flags.disable_dmcu = false;
+				break;
+			default:
+				init_data.flags.disable_dmcu = true;
+			}
 			break;
 		case IP_VERSION(1, 0, 0):
 		case IP_VERSION(1, 0, 1):
@ -1556,7 +1569,11 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
 			goto error;
 		}
-#endif
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) {
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+			goto error;
+		}
+#endif /* CONFIG_DRM_AMD_DC_DCN */
 	}

 	if (amdgpu_dm_initialize_drm_device(adev)) {
@ -4565,7 +4582,8 @@ static void get_min_max_dc_plane_scaling(struct drm_device *dev,
 }


-static int fill_dc_scaling_info(const struct drm_plane_state *state,
+static int fill_dc_scaling_info(struct amdgpu_device *adev,
+				const struct drm_plane_state *state,
 				struct dc_scaling_info *scaling_info)
 {
 	int scale_w, scale_h, min_downscale, max_upscale;
@ -4579,7 +4597,8 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state,
 	/*
 	 * For reasons we don't (yet) fully understand a non-zero
 	 * src_y coordinate into an NV12 buffer can cause a
-	 * system hang. To avoid hangs (and maybe be overly cautious)
+	 * system hang on DCN1x.
+	 * To avoid hangs (and maybe be overly cautious)
 	 * let's reject both non-zero src_x and src_y.
 	 *
 	 * We currently know of only one use-case to reproduce a
@ -4587,10 +4606,10 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state,
 	 * is to gesture the YouTube Android app into full screen
 	 * on ChromeOS.
 	 */
-	if (state->fb &&
-	    state->fb->format->format == DRM_FORMAT_NV12 &&
-	    (scaling_info->src_rect.x != 0 ||
-	     scaling_info->src_rect.y != 0))
+	if (((adev->ip_versions[DCE_HWIP][0] == IP_VERSION(1, 0, 0)) ||
+	    (adev->ip_versions[DCE_HWIP][0] == IP_VERSION(1, 0, 1))) &&
+	    (state->fb && state->fb->format->format == DRM_FORMAT_NV12 &&
+	    (scaling_info->src_rect.x != 0 || scaling_info->src_rect.y != 0)))
 		return -EINVAL;

 	scaling_info->src_rect.width = state->src_w >> 16;
@ -5496,7 +5515,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	int ret;
 	bool force_disable_dcc = false;

-	ret = fill_dc_scaling_info(plane_state, &scaling_info);
+	ret = fill_dc_scaling_info(adev, plane_state, &scaling_info);
 	if (ret)
 		return ret;

@ -6070,7 +6089,7 @@ static void apply_dsc_policy_for_stream(struct amdgpu_dm_connector *aconnector,
 	if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_bits_per_pixel)
 		stream->timing.dsc_cfg.bits_per_pixel = aconnector->dsc_settings.dsc_bits_per_pixel;
 }
-#endif
+#endif /* CONFIG_DRM_AMD_DC_DCN */

 /**
 * DOC: FreeSync Video
@ -7241,8 +7260,8 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 	struct drm_connector_state *new_con_state;
 	struct amdgpu_dm_connector *aconnector;
 	struct dm_connector_state *dm_conn_state;
-	int i, j, clock;
-	int vcpi, pbn_div, pbn = 0;
+	int i, j;
+	int vcpi, pbn_div, pbn, slot_num = 0;

 	for_each_new_connector_in_state(state, connector, new_con_state, i) {

@ -7270,17 +7289,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 		if (!stream)
 			continue;

-		if (stream->timing.flags.DSC != 1) {
-			drm_dp_mst_atomic_enable_dsc(state,
-						     aconnector->port,
-						     dm_conn_state->pbn,
-						     0,
-						     false);
-			continue;
-		}
-
 		pbn_div = dm_mst_get_pbn_divider(stream->link);
-		clock = stream->timing.pix_clk_100hz / 10;
 		/* pbn is calculated by compute_mst_dsc_configs_for_state*/
 		for (j = 0; j < dc_state->stream_count; j++) {
 			if (vars[j].aconnector == aconnector) {
@ -7289,6 +7298,23 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 			}
 		}

+		if (j == dc_state->stream_count)
+			continue;
+
+		slot_num = DIV_ROUND_UP(pbn, pbn_div);
+
+		if (stream->timing.flags.DSC != 1) {
+			dm_conn_state->pbn = pbn;
+			dm_conn_state->vcpi_slots = slot_num;
+
+			drm_dp_mst_atomic_enable_dsc(state,
+						     aconnector->port,
+						     dm_conn_state->pbn,
+						     0,
+						     false);
+			continue;
+		}
+
 		vcpi = drm_dp_mst_atomic_enable_dsc(state,
 						    aconnector->port,
 						    pbn, pbn_div,
@ -7552,7 +7578,7 @@ static int dm_plane_atomic_check(struct drm_plane *plane,
 	if (ret)
 		return ret;

-	ret = fill_dc_scaling_info(new_plane_state, &scaling_info);
+	ret = fill_dc_scaling_info(adev, new_plane_state, &scaling_info);
 	if (ret)
 		return ret;

@ -9000,7 +9026,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix;
 		}

-		fill_dc_scaling_info(new_plane_state,
+		fill_dc_scaling_info(dm->adev, new_plane_state,
 				     &bundle->scaling_infos[planes_count]);

 		bundle->surface_updates[planes_count].scaling_info =
@ -10787,7 +10813,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,

 		ret = drm_atomic_add_affected_connectors(state, crtc);
 		if (ret)
-			return ret;
+			goto fail;

 		ret = drm_atomic_add_affected_planes(state, crtc);
 		if (ret)
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@ -78,12 +78,10 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size,

 	wr_buf_ptr = wr_buf;

-	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
-
-		/* r is bytes not be copied */
-	if (r >= wr_buf_size) {
-		DRM_DEBUG_DRIVER("user data not be read\n");
-		return -EINVAL;
+	/* r is bytes not be copied */
+	if (copy_from_user(wr_buf_ptr, buf, wr_buf_size)) {
+		DRM_DEBUG_DRIVER("user data could not be read successfully\n");
+		return -EFAULT;
 	}

 	/* check number of parameters. isspace could not differ space and \n */
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@ -534,13 +534,14 @@ static int kbps_to_peak_pbn(int kbps)

 static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params,
 		struct dsc_mst_fairness_vars *vars,
-		int count)
+		int count,
+		int k)
 {
 	int i;

 	for (i = 0; i < count; i++) {
 		memset(&params[i].timing->dsc_cfg, 0, sizeof(params[i].timing->dsc_cfg));
-		if (vars[i].dsc_enabled && dc_dsc_compute_config(
+		if (vars[i + k].dsc_enabled && dc_dsc_compute_config(
 					params[i].sink->ctx->dc->res_pool->dscs[0],
 					&params[i].sink->dsc_caps.dsc_dec_caps,
 					params[i].sink->ctx->dc->debug.dsc_min_slice_height_override,
@ -553,7 +554,7 @@ static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *p
 			if (params[i].bpp_overwrite)
 				params[i].timing->dsc_cfg.bits_per_pixel = params[i].bpp_overwrite;
 			else
-				params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
+				params[i].timing->dsc_cfg.bits_per_pixel = vars[i + k].bpp_x16;

 			if (params[i].num_slices_h)
 				params[i].timing->dsc_cfg.num_slices_h = params[i].num_slices_h;
@ -586,7 +587,8 @@ static void increase_dsc_bpp(struct drm_atomic_state *state,
 			     struct dc_link *dc_link,
 			     struct dsc_mst_fairness_params *params,
 			     struct dsc_mst_fairness_vars *vars,
-			     int count)
+			     int count,
+			     int k)
 {
 	int i;
 	bool bpp_increased[MAX_PIPES];
@ -601,8 +603,9 @@ static void increase_dsc_bpp(struct drm_atomic_state *state,
 	pbn_per_timeslot = dm_mst_get_pbn_divider(dc_link);

 	for (i = 0; i < count; i++) {
-		if (vars[i].dsc_enabled) {
-			initial_slack[i] = kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i].pbn;
+		if (vars[i + k].dsc_enabled) {
+			initial_slack[i] =
+			kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn;
 			bpp_increased[i] = false;
 			remaining_to_increase += 1;
 		} else {
@ -629,7 +632,7 @@ static void increase_dsc_bpp(struct drm_atomic_state *state,
 		link_timeslots_used = 0;

 		for (i = 0; i < count; i++)
-			link_timeslots_used += DIV_ROUND_UP(vars[i].pbn, pbn_per_timeslot);
+			link_timeslots_used += DIV_ROUND_UP(vars[i + k].pbn, pbn_per_timeslot);

 		fair_pbn_alloc = (63 - link_timeslots_used) / remaining_to_increase * pbn_per_timeslot;

@ -682,7 +685,8 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 			    struct dc_link *dc_link,
 			    struct dsc_mst_fairness_params *params,
 			    struct dsc_mst_fairness_vars *vars,
-			    int count)
+			    int count,
+			    int k)
 {
 	int i;
 	bool tried[MAX_PIPES];
@ -692,8 +696,8 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 	int remaining_to_try = 0;

 	for (i = 0; i < count; i++) {
-		if (vars[i].dsc_enabled
-				&& vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16
+		if (vars[i + k].dsc_enabled
+				&& vars[i + k].bpp_x16 == params[i].bw_range.max_target_bpp_x16
 				&& params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) {
 			kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps;
 			tried[i] = false;
@ -748,9 +752,10 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 					     struct dc_state *dc_state,
 					     struct dc_link *dc_link,
-					     struct dsc_mst_fairness_vars *vars)
+					     struct dsc_mst_fairness_vars *vars,
+					     int *link_vars_start_index)
 {
-	int i;
+	int i, k;
 	struct dc_stream_state *stream;
 	struct dsc_mst_fairness_params params[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
@ -768,11 +773,17 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		if (stream->link != dc_link)
 			continue;

+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+		if (!aconnector)
+			continue;
+
+		if (!aconnector->port)
+			continue;
+
 		stream->timing.flags.DSC = 0;

 		params[count].timing = &stream->timing;
 		params[count].sink = stream->sink;
-		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 		params[count].aconnector = aconnector;
 		params[count].port = aconnector->port;
 		params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable;
@ -794,44 +805,55 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,

 		count++;
 	}
+
+	if (count == 0) {
+		ASSERT(0);
+		return true;
+	}
+
+	/* k is start index of vars for current phy link used by mst hub */
+	k = *link_vars_start_index;
+	/* set vars start index for next mst hub phy link */
+	*link_vars_start_index += count;
+
 	/* Try no compression */
 	for (i = 0; i < count; i++) {
-		vars[i].aconnector = params[i].aconnector;
-		vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
-		vars[i].dsc_enabled = false;
-		vars[i].bpp_x16 = 0;
+		vars[i + k].aconnector = params[i].aconnector;
+		vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+		vars[i + k].dsc_enabled = false;
+		vars[i + k].bpp_x16 = 0;
 		if (drm_dp_atomic_find_vcpi_slots(state,
 						 params[i].port->mgr,
 						 params[i].port,
-						 vars[i].pbn,
+						 vars[i + k].pbn,
 						 dm_mst_get_pbn_divider(dc_link)) < 0)
 			return false;
 	}
 	if (!drm_dp_mst_atomic_check(state) && !debugfs_overwrite) {
-		set_dsc_configs_from_fairness_vars(params, vars, count);
+		set_dsc_configs_from_fairness_vars(params, vars, count, k);
 		return true;
 	}

 	/* Try max compression */
 	for (i = 0; i < count; i++) {
 		if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) {
-			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
-			vars[i].dsc_enabled = true;
-			vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
+			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
+			vars[i + k].dsc_enabled = true;
+			vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
 			if (drm_dp_atomic_find_vcpi_slots(state,
 							  params[i].port->mgr,
 							  params[i].port,
-							  vars[i].pbn,
+							  vars[i + k].pbn,
 							  dm_mst_get_pbn_divider(dc_link)) < 0)
 				return false;
 		} else {
-			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
-			vars[i].dsc_enabled = false;
-			vars[i].bpp_x16 = 0;
+			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+			vars[i + k].dsc_enabled = false;
+			vars[i + k].bpp_x16 = 0;
 			if (drm_dp_atomic_find_vcpi_slots(state,
 							  params[i].port->mgr,
 							  params[i].port,
-							  vars[i].pbn,
+							  vars[i + k].pbn,
 							  dm_mst_get_pbn_divider(dc_link)) < 0)
 				return false;
 		}
@ -840,15 +862,76 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		return false;

 	/* Optimize degree of compression */
-	increase_dsc_bpp(state, dc_link, params, vars, count);
+	increase_dsc_bpp(state, dc_link, params, vars, count, k);

-	try_disable_dsc(state, dc_link, params, vars, count);
+	try_disable_dsc(state, dc_link, params, vars, count, k);

-	set_dsc_configs_from_fairness_vars(params, vars, count);
+	set_dsc_configs_from_fairness_vars(params, vars, count, k);

 	return true;
 }

+static bool is_dsc_need_re_compute(
+	struct drm_atomic_state *state,
+	struct dc_state *dc_state,
+	struct dc_link *dc_link)
+{
+	int i;
+	bool is_dsc_need_re_compute = false;
+
+	/* only check phy used by mst branch */
+	if (dc_link->type != dc_connection_mst_branch)
+		return false;
+
+	/* check if there is mode change in new request */
+	for (i = 0; i < dc_state->stream_count; i++) {
+		struct amdgpu_dm_connector *aconnector;
+		struct dc_stream_state *stream;
+		struct drm_crtc_state *new_crtc_state;
+		struct drm_connector_state *new_conn_state;
+
+		stream = dc_state->streams[i];
+
+		if (!stream)
+			continue;
+
+		/* check if stream using the same link for mst */
+		if (stream->link != dc_link)
+			continue;
+
+		aconnector = (struct amdgpu_dm_connector *) stream->dm_stream_context;
+		if (!aconnector)
+			continue;
+
+		new_conn_state = drm_atomic_get_new_connector_state(state, &aconnector->base);
+
+		if (!new_conn_state)
+			continue;
+
+		if (IS_ERR(new_conn_state))
+			continue;
+
+		if (!new_conn_state->crtc)
+			continue;
+
+		new_crtc_state = drm_atomic_get_new_crtc_state(state, new_conn_state->crtc);
+
+		if (!new_crtc_state)
+			continue;
+
+		if (IS_ERR(new_crtc_state))
+			continue;
+
+		if (new_crtc_state->enable && new_crtc_state->active) {
+			if (new_crtc_state->mode_changed || new_crtc_state->active_changed ||
+				new_crtc_state->connectors_changed)
+				is_dsc_need_re_compute = true;
+		}
+	}
+
+	return is_dsc_need_re_compute;
+}
+
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 				       struct dc_state *dc_state,
 				       struct dsc_mst_fairness_vars *vars)
@ -857,6 +940,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 	struct dc_stream_state *stream;
 	bool computed_streams[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
+	int link_vars_start_index = 0;

 	for (i = 0; i < dc_state->stream_count; i++)
 		computed_streams[i] = false;
@ -881,8 +965,12 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 		if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK)
 			return false;

+		if (!is_dsc_need_re_compute(state, dc_state, stream->link))
+			continue;
+
 		mutex_lock(&aconnector->mst_mgr.lock);
-		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars)) {
+		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link,
+			vars, &link_vars_start_index)) {
 			mutex_unlock(&aconnector->mst_mgr.lock);
 			return false;
 		}
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@ -1085,6 +1085,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 		struct dc_stream_state *old_stream =
 				dc->current_state->res_ctx.pipe_ctx[i].stream;
 		bool should_disable = true;
+		bool pipe_split_change =
+			context->res_ctx.pipe_ctx[i].top_pipe != dc->current_state->res_ctx.pipe_ctx[i].top_pipe;

 		for (j = 0; j < context->stream_count; j++) {
 			if (old_stream == context->streams[j]) {
@ -1092,6 +1094,9 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 				break;
 			}
 		}
+		if (!should_disable && pipe_split_change)
+			should_disable = true;
+
 		if (should_disable && old_stream) {
 			dc_rem_all_planes_for_stream(dc, old_stream, dangling_context);
 			disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context);
@ -1887,6 +1892,7 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context)
 	return false;
 }

+#ifdef CONFIG_DRM_AMD_DC_DCN
 /* Perform updates here which need to be deferred until next vupdate
 *
 * i.e. blnd lut, 3dlut, and shaper lut bypass regs are double buffered
@ -1896,7 +1902,6 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context)
 */
 static void process_deferred_updates(struct dc *dc)
 {
-#ifdef CONFIG_DRM_AMD_DC_DCN
 	int i = 0;

 	if (dc->debug.enable_mem_low_power.bits.cm) {
@ -1905,8 +1910,8 @@ static void process_deferred_updates(struct dc *dc)
 			if (dc->res_pool->dpps[i]->funcs->dpp_deferred_update)
 				dc->res_pool->dpps[i]->funcs->dpp_deferred_update(dc->res_pool->dpps[i]);
 	}
-#endif
 }
+#endif /* CONFIG_DRM_AMD_DC_DCN */

 void dc_post_update_surfaces_to_stream(struct dc *dc)
 {
@ -1933,7 +1938,9 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 			dc->hwss.disable_plane(dc, &context->res_ctx.pipe_ctx[i]);
 		}

+#ifdef CONFIG_DRM_AMD_DC_DCN
 	process_deferred_updates(dc);
+#endif

 	dc->hwss.optimize_bandwidth(dc, context);

@ -3603,7 +3610,8 @@ bool dc_enable_dmub_notifications(struct dc *dc)
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* YELLOW_CARP B0 USB4 DPIA needs dmub notifications for interrupts */
 	if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP &&
-	    dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0)
+	    dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 &&
+	    !dc->debug.dpia_debug.bits.disable_dpia)
 		return true;
 #endif
 	/* dmub aux needs dmub notifications to be enabled */
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@ -4279,6 +4279,8 @@ void core_link_enable_stream(
 			 */
 			if (status != DC_FAIL_DP_LINK_TRAINING ||
 					pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+				if (false == stream->link->link_status.link_active)
+					disable_link(stream->link, pipe_ctx->stream->signal);
 				BREAK_TO_DEBUGGER();
 				return;
 			}
@ -4768,7 +4770,7 @@ uint32_t dc_bandwidth_in_kbps_from_timing(
 				timing->dsc_cfg.bits_per_pixel,
 				timing->dsc_cfg.num_slices_h,
 				timing->dsc_cfg.is_dp);
-#endif
+#endif /* CONFIG_DRM_AMD_DC_DCN */

 	switch (timing->display_color_depth) {
 	case COLOR_DEPTH_666:
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@ -5329,6 +5329,14 @@ bool dc_link_dp_set_test_pattern(
 			return false;

 		if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+			if (test_pattern == DP_TEST_PATTERN_SQUARE_PULSE)
+				core_link_write_dpcd(link,
+						DP_LINK_SQUARE_PATTERN,
+						p_custom_pattern,
+						1);
+
+#endif
 			/* tell receiver that we are sending qualification
 			 * pattern DP 1.2 or later - DP receiver's link quality
 			 * pattern is set using DPCD LINK_QUAL_LANEx_SET
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
@ -236,6 +236,23 @@ static struct link_encoder *get_link_enc_used_by_link(

 	return link_enc;
 }
+/* Clear all link encoder assignments. */
+static void clear_enc_assignments(struct dc_state *state)
+{
+	int i;
+	enum engine_id eng_id;
+	struct dc_stream_state *stream;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].valid = false;
+		eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].eng_id;
+		stream = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].stream;
+		if (eng_id != ENGINE_ID_UNKNOWN)
+			state->res_ctx.link_enc_cfg_ctx.link_enc_avail[eng_id - ENGINE_ID_DIGA] = eng_id;
+		if (stream)
+			stream->link_enc = NULL;
+	}
+}

 void link_enc_cfg_init(
 		struct dc *dc,
@ -250,6 +267,8 @@ void link_enc_cfg_init(
 			state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i] = ENGINE_ID_UNKNOWN;
 	}

+	clear_enc_assignments(state);
+
 	state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_STEADY;
 }

@ -265,6 +284,9 @@ void link_enc_cfg_link_encs_assign(

 	ASSERT(state->stream_count == stream_count);

+	if (stream_count == 0)
+		clear_enc_assignments(state);
+
 	/* Release DIG link encoder resources before running assignment algorithm. */
 	for (i = 0; i < stream_count; i++)
 		dc->res_pool->funcs->link_enc_unassign(state, streams[i]);
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@ -47,7 +47,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;

-#define DC_VER "3.2.159"
+#define DC_VER "3.2.160"

 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@ -675,6 +675,7 @@ struct dc_debug_options {
 #endif
 	union mem_low_power_enable_options enable_mem_low_power;
 	union root_clock_optimization_options root_clock_optimization;
+	bool hpo_optimization;
 	bool force_vblank_alignment;

 	/* Enable dmub aux for legacy ddc */
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@ -898,6 +898,9 @@ struct dpcd_usb4_dp_tunneling_info {
 #ifndef DP_DFP_CAPABILITY_EXTENSION_SUPPORT
 #define DP_DFP_CAPABILITY_EXTENSION_SUPPORT		0x0A3
 #endif
+#ifndef DP_LINK_SQUARE_PATTERN
+#define DP_LINK_SQUARE_PATTERN				0x10F
+#endif
 #ifndef DP_DSC_CONFIGURATION
 #define DP_DSC_CONFIGURATION				0x161
 #endif
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@ -671,6 +671,7 @@ struct dce_hwseq_registers {
 	uint32_t MC_VM_FB_LOCATION_BASE;
 	uint32_t MC_VM_FB_LOCATION_TOP;
 	uint32_t MC_VM_FB_OFFSET;
+	uint32_t HPO_TOP_HW_CONTROL;
 };
 /* set field name */
 #define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@ -1152,7 +1153,8 @@ struct dce_hwseq_registers {
 	type DOMAIN_PGFSM_PWR_STATUS;\
 	type HPO_HDMISTREAMCLK_G_GATE_DIS;\
 	type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;\
-	type I2C_LIGHT_SLEEP_FORCE;
+	type I2C_LIGHT_SLEEP_FORCE;\
+	type HPO_IO_EN;

 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@ -1244,6 +1244,12 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 #endif
 	if (dc_is_dp_signal(pipe_ctx->stream->signal))
 		dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISCONNECT_DIG_FE_BE);
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (dc->hwseq->funcs.setup_hpo_hw_control && is_dp_128b_132b_signal(pipe_ctx))
+		dc->hwseq->funcs.setup_hpo_hw_control(dc->hwseq, false);
+#endif
+
 }

 void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@ -231,7 +231,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)

 		if (!s->blank_en)
 			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
-				"%  8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
+				"  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
 				"  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
 				pool->hubps[i]->inst, dlg_regs->refcyc_h_blank_end, dlg_regs->dlg_vblank_end, dlg_regs->min_dst_y_next_start,
 				dlg_regs->refcyc_per_htotal, dlg_regs->refcyc_x_after_scaler, dlg_regs->dst_y_after_scaler,
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@ -2397,6 +2397,9 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	 * BY this, it is logic clean to separate stream and link
 	 */
 	if (is_dp_128b_132b_signal(pipe_ctx)) {
+		if (pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control)
+			pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control(
+				pipe_ctx->stream->ctx->dc->hwseq, true);
 		setup_dp_hpo_stream(pipe_ctx, true);
 		pipe_ctx->stream_res.hpo_dp_stream_enc->funcs->enable_stream(
 				pipe_ctx->stream_res.hpo_dp_stream_enc);
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@ -1381,13 +1381,11 @@ int mpcc3_release_rmu(struct mpc *mpc, int mpcc_id)

 }

-static void mpc3_mpc_init(struct mpc *mpc)
+static void mpc3_set_mpc_mem_lp_mode(struct mpc *mpc)
 {
 	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
 	int mpcc_id;

-	mpc1_mpc_init(mpc);
-
 	if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) {
 		if (mpc30->mpc_mask->MPC_RMU0_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPC_RMU1_MEM_LOW_PWR_MODE) {
 			REG_UPDATE(MPC_RMU_MEM_PWR_CTRL, MPC_RMU0_MEM_LOW_PWR_MODE, 3);
@ -1405,7 +1403,7 @@ const struct mpc_funcs dcn30_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
-	.mpc_init = mpc3_mpc_init,
+	.mpc_init = mpc1_mpc_init,
 	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
 	.cursor_lock = mpc1_cursor_lock,
@ -1432,6 +1430,7 @@ const struct mpc_funcs dcn30_mpc_funcs = {
 	.power_on_mpc_mem_pwr = mpc3_power_on_ogam_lut,
 	.get_mpc_out_mux = mpc1_get_mpc_out_mux,
 	.set_bg_color = mpc1_set_bg_color,
+	.set_mpc_mem_lp_mode = mpc3_set_mpc_mem_lp_mode,
 };

 void dcn30_mpc_construct(struct dcn30_mpc *mpc30,
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@ -2128,10 +2128,10 @@ static noinline void dcn30_calculate_wm_and_dlg_fp(
 		int pipe_cnt,
 		int vlevel)
 {
+	int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb;
 	int i, pipe_idx;
-	double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
-	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] !=
-			dm_dram_clock_change_unsupported;
+	double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][maxMpcComb];
+	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] != dm_dram_clock_change_unsupported;

 	if (context->bw_ctx.dml.soc.min_dcfclk > dcfclk)
 		dcfclk = context->bw_ctx.dml.soc.min_dcfclk;
@ -2207,6 +2207,7 @@ static noinline void dcn30_calculate_wm_and_dlg_fp(
 		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us;
 		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us;
 	}
+
 	context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@ -66,6 +66,45 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name

+static void enable_memory_low_power(struct dc *dc)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	if (dc->debug.enable_mem_low_power.bits.dmcu) {
+		// Force ERAM to shutdown if DMCU is not enabled
+		if (dc->debug.disable_dmcu || dc->config.disable_dmcu) {
+			REG_UPDATE(DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, 3);
+		}
+	}
+
+	// Set default OPTC memory power states
+	if (dc->debug.enable_mem_low_power.bits.optc) {
+		// Shutdown when unassigned and light sleep in VBLANK
+		REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1);
+	}
+
+	if (dc->debug.enable_mem_low_power.bits.vga) {
+		// Power down VGA memory
+		REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1);
+	}
+
+	if (dc->debug.enable_mem_low_power.bits.mpc)
+		dc->res_pool->mpc->funcs->set_mpc_mem_lp_mode(dc->res_pool->mpc);
+
+
+	if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) {
+		// Power down VPGs
+		for (i = 0; i < dc->res_pool->stream_enc_count; i++)
+			dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg);
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++)
+			dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg);
+#endif
+	}
+
+}
+
 void dcn31_init_hw(struct dc *dc)
 {
 	struct abm **abms = dc->res_pool->multiple_abms;
@ -108,35 +147,7 @@ void dcn31_init_hw(struct dc *dc)
 	if (res_pool->dccg->funcs->dccg_init)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);

-	if (dc->debug.enable_mem_low_power.bits.dmcu) {
-		// Force ERAM to shutdown if DMCU is not enabled
-		if (dc->debug.disable_dmcu || dc->config.disable_dmcu) {
-			REG_UPDATE(DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, 3);
-		}
-	}
-
-	// Set default OPTC memory power states
-	if (dc->debug.enable_mem_low_power.bits.optc) {
-		// Shutdown when unassigned and light sleep in VBLANK
-		REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1);
-	}
-
-	if (dc->debug.enable_mem_low_power.bits.vga) {
-		// Power down VGA memory
-		REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1);
-	}
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-	if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) {
-		// Power down VPGs
-		for (i = 0; i < dc->res_pool->stream_enc_count; i++)
-			dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg);
-#if defined(CONFIG_DRM_AMD_DC_DP2_0)
-		for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++)
-			dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg);
-#endif
-	}
-#endif
+	enable_memory_low_power(dc);

 	if (dc->ctx->dc_bios->fw_info_valid) {
 		res_pool->ref_clocks.xtalin_clock_inKhz =
@ -264,6 +275,9 @@ void dcn31_init_hw(struct dc *dc)
 	if (dc->debug.enable_mem_low_power.bits.i2c)
 		REG_UPDATE(DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, 1);

+	if (hws->funcs.setup_hpo_hw_control)
+		hws->funcs.setup_hpo_hw_control(hws, false);
+
 	if (!dc->debug.disable_clock_gate) {
 		/* enable all DCN clock gating */
 		REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
@ -597,3 +611,9 @@ void dcn31_reset_hw_ctx_wrap(
 	/* New dc_state in the process of being applied to hardware. */
 	dc->current_state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_TRANSIENT;
 }
+
+void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable)
+{
+	if (hws->ctx->dc->debug.hpo_optimization)
+		REG_UPDATE(HPO_TOP_HW_CONTROL, HPO_IO_EN, !!enable);
+}
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
@ -54,5 +54,6 @@ void dcn31_reset_hw_ctx_wrap(
 bool dcn31_is_abm_supported(struct dc *dc,
 		struct dc_state *context, struct dc_stream_state *stream);
 void dcn31_init_pipes(struct dc *dc, struct dc_state *context);
+void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable);

 #endif /* __DC_HWSS_DCN31_H__ */
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@ -137,6 +137,7 @@ static const struct hwseq_private_funcs dcn31_private_funcs = {
 	.dccg_init = dcn20_dccg_init,
 	.set_blend_lut = dcn30_set_blend_lut,
 	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
+	.setup_hpo_hw_control = dcn31_setup_hpo_hw_control,
 };

 void dcn31_hw_sequencer_construct(struct dc *dc)
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@ -860,7 +860,8 @@ static const struct dccg_mask dccg_mask = {
 	SR(D6VGA_CONTROL), \
 	SR(DC_IP_REQUEST_CNTL), \
 	SR(AZALIA_AUDIO_DTO), \
-	SR(AZALIA_CONTROLLER_CLOCK_GATING)
+	SR(AZALIA_CONTROLLER_CLOCK_GATING), \
+	SR(HPO_TOP_HW_CONTROL)

 static const struct dce_hwseq_registers hwseq_reg = {
 		HWSEQ_DCN31_REG_LIST()
@ -898,7 +899,8 @@ static const struct dce_hwseq_registers hwseq_reg = {
 	HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_UNASSIGNED_PWR_MODE, mask_sh), \
 	HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_VBLANK_PWR_MODE, mask_sh), \
 	HWS_SF(, MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, mask_sh), \
-	HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+	HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh), \
+	HWS_SF(, HPO_TOP_HW_CONTROL, HPO_IO_EN, mask_sh)

 static const struct dce_hwseq_shift hwseq_shift = {
 		HWSEQ_DCN31_MASK_SH_LIST(__SHIFT)
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@ -3576,16 +3576,9 @@ static double TruncToValidBPP(
 		MinDSCBPP = 8;
 		MaxDSCBPP = 3 * DSCInputBitPerComponent - 1.0 / 16;
 	} else {
-		if (Output == dm_hdmi) {
-			NonDSCBPP0 = 24;
-			NonDSCBPP1 = 24;
-			NonDSCBPP2 = 24;
-		}
-		else {
-			NonDSCBPP0 = 16;
-			NonDSCBPP1 = 20;
-			NonDSCBPP2 = 24;
-		}
+		NonDSCBPP0 = 16;
+		NonDSCBPP1 = 20;
+		NonDSCBPP2 = 24;

 		if (Format == dm_n422) {
 			MinDSCBPP = 7;
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@ -3892,15 +3892,11 @@ static double TruncToValidBPP(
 		MinDSCBPP = 8;
 		MaxDSCBPP = 3 * DSCInputBitPerComponent - 1.0 / 16;
 	} else {
-		if (Output == dm_hdmi) {
-			NonDSCBPP0 = 24;
-			NonDSCBPP1 = 24;
-			NonDSCBPP2 = 24;
-		} else {
-			NonDSCBPP0 = 16;
-			NonDSCBPP1 = 20;
-			NonDSCBPP2 = 24;
-		}
+
+		NonDSCBPP0 = 16;
+		NonDSCBPP1 = 20;
+		NonDSCBPP2 = 24;
+
 		if (Format == dm_n422) {
 			MinDSCBPP = 7;
 			MaxDSCBPP = 2 * DSCInputBitPerComponent - 1.0 / 16.0;
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@ -367,6 +367,7 @@ struct mpc_funcs {
 	void (*set_bg_color)(struct mpc *mpc,
 			struct tg_color *bg_color,
 			int mpcc_id);
+	void (*set_mpc_mem_lp_mode)(struct mpc *mpc);
 };

 #endif
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@ -143,6 +143,7 @@ struct hwseq_private_funcs {
 			const struct dc_plane_state *plane_state);
 	void (*PLAT_58856_wa)(struct dc_state *context,
 			struct pipe_ctx *pipe_ctx);
+	void (*setup_hpo_hw_control)(const struct dce_hwseq *hws, bool enable);
 };

 struct dce_hwseq {
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@ -238,6 +238,7 @@ struct dmub_srv_hw_params {
 	bool load_inst_const;
 	bool skip_panel_power_sequence;
 	bool disable_z10;
+	bool power_optimization;
 	bool dpia_supported;
 	bool disable_dpia;
 };
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@ -46,10 +46,10 @@

 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0x9525efb5
+#define DMUB_FW_VERSION_GIT_HASH 0x1d82d23e
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 90
+#define DMUB_FW_VERSION_REVISION 91
 #define DMUB_FW_VERSION_TEST 0
 #define DMUB_FW_VERSION_VBIOS 0
 #define DMUB_FW_VERSION_HOTFIX 0
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@ -340,6 +340,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu
 	boot_options.bits.z10_disable = params->disable_z10;
 	boot_options.bits.dpia_supported = params->dpia_supported;
 	boot_options.bits.enable_dpia = params->disable_dpia ? 0 : 1;
+	boot_options.bits.power_optimization = params->power_optimization;

 	boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0;

--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@ -2094,6 +2094,10 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	} else if (DEVICE_ATTR_IS(pp_dpm_dclk)) {
 		if (!(asic_type == CHIP_VANGOGH || asic_type == CHIP_SIENNA_CICHLID))
 			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(pp_power_profile_mode)) {
+		if (!adev->powerplay.pp_funcs->get_power_profile_mode ||
+		    amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP)
+			*states = ATTR_STATE_UNSUPPORTED;
 	}

 	switch (asic_type) {
--- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h
@ -51,7 +51,7 @@
 #define PPSMC_MSG_PowerUpVcn                    0x07 ///< Power up VCN; VCN is power gated by default
 #define PPSMC_MSG_SetHardMinVcn                 0x08 ///< For wireless display
 #define PPSMC_MSG_SetSoftMinGfxclk              0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz
-#define PPSMC_MSG_ActiveProcessNotify           0x0A ///< Set active work load type
+#define PPSMC_MSG_ActiveProcessNotify           0x0A ///< Deprecated (Not to be used)
 #define PPSMC_MSG_ForcePowerDownGfx             0x0B ///< Force power down GFX, i.e. enter GFXOFF
 #define PPSMC_MSG_PrepareMp1ForUnload           0x0C ///< Prepare PMFW for GFX driver unload
 #define PPSMC_MSG_SetDriverDramAddrHigh         0x0D ///< Set high 32 bits of DRAM address for Driver table transfer
@ -63,7 +63,7 @@
 #define PPSMC_MSG_SetHardMinSocclkByFreq        0x13 ///< Set hard min for SOC CLK
 #define PPSMC_MSG_SetSoftMinFclk                0x14 ///< Set hard min for FCLK
 #define PPSMC_MSG_SetSoftMinVcn                 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK)
-#define PPSMC_MSG_SPARE0                        0x16 ///< Spared
+#define PPSMC_MSG_SPARE                         0x16 ///< Spare
 #define PPSMC_MSG_GetGfxclkFrequency            0x17 ///< Get GFX clock frequency
 #define PPSMC_MSG_GetFclkFrequency              0x18 ///< Get FCLK frequency
 #define PPSMC_MSG_AllowGfxOff                   0x19 ///< Inform PMFW of allowing GFXOFF entry
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@ -875,34 +875,30 @@ pp_dpm_get_vce_clock_state(void *handle, unsigned idx)
 static int pp_get_power_profile_mode(void *handle, char *buf)
 {
 	struct pp_hwmgr *hwmgr = handle;
+	int ret;

-	if (!hwmgr || !hwmgr->pm_en || !buf)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->hwmgr_func->get_power_profile_mode)
+		return -EOPNOTSUPP;
+	if (!buf)
 		return -EINVAL;

-	if (hwmgr->hwmgr_func->get_power_profile_mode == NULL) {
-		pr_info_ratelimited("%s was not implemented.\n", __func__);
-		return snprintf(buf, PAGE_SIZE, "\n");
-	}
-
-	return hwmgr->hwmgr_func->get_power_profile_mode(hwmgr, buf);
+	mutex_lock(&hwmgr->smu_lock);
+	ret = hwmgr->hwmgr_func->get_power_profile_mode(hwmgr, buf);
+	mutex_unlock(&hwmgr->smu_lock);
+	return ret;
 }

 static int pp_set_power_profile_mode(void *handle, long *input, uint32_t size)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = -EINVAL;
+	int ret = -EOPNOTSUPP;

-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->hwmgr_func->set_power_profile_mode)
 		return ret;

-	if (hwmgr->hwmgr_func->set_power_profile_mode == NULL) {
-		pr_info_ratelimited("%s was not implemented.\n", __func__);
-		return ret;
-	}
-
 	if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) {
 		pr_debug("power profile setting is for manual dpm mode only.\n");
-		return ret;
+		return -EINVAL;
 	}

 	mutex_lock(&hwmgr->smu_lock);
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@ -1024,6 +1024,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	uint32_t min_freq, max_freq = 0;
 	uint32_t ret = 0;

+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now);
@ -1065,7 +1067,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;

-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@ -1081,7 +1083,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;

-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				min_freq, max_freq);
 		}
@ -1456,6 +1458,8 @@ static int smu10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;

+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0],
 			title[1], title[2], title[3], title[4], title[5]);

--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@ -4914,6 +4914,8 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int size = 0;
 	uint32_t i, now, clock, pcie_speed;

+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_API_GetSclkFrequency, &clock);
@ -4963,7 +4965,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			for (i = 0; i < odn_sclk_table->num_of_pl; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
 					i, odn_sclk_table->entries[i].clock/100,
@ -4972,7 +4974,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 			for (i = 0; i < odn_mclk_table->num_of_pl; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
 					i, odn_mclk_table->entries[i].clock/100,
@ -4981,7 +4983,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.sclk_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
@ -5518,6 +5520,8 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;

+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%s %16s %16s %16s %16s %16s %16s %16s\n",
 			title[0], title[1], title[2], title[3],
 			title[4], title[5], title[6], title[7]);
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
@ -1550,6 +1550,8 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 	uint32_t i, now;
 	int size = 0;

+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		now = PHM_GET_FIELD(cgs_read_ind_register(hwmgr->device,
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
@ -109,6 +109,19 @@ int phm_irq_process(struct amdgpu_device *adev,
 			   struct amdgpu_irq_src *source,
 			   struct amdgpu_iv_entry *entry);

+/*
+ * Helper function to make sysfs_emit_at() happy. Align buf to
+ * the current page boundary and record the offset.
+ */
+static inline void phm_get_sysfs_buf(char **buf, int *offset)
+{
+	if (!*buf || !offset)
+		return;
+
+	*offset = offset_in_page(*buf);
+	*buf -= *offset;
+}
+
 int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr);

 void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@ -4548,6 +4548,8 @@ static int vega10_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 	int ret = 0;
 	int size = 0;

+	phm_get_sysfs_buf(&buf, &size);
+
 	ret = vega10_get_enabled_smc_features(hwmgr, &features_enabled);
 	PP_ASSERT_WITH_CODE(!ret,
 			"[EnableAllSmuFeatures] Failed to get enabled smc features!",
@ -4637,6 +4639,8 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,

 	int i, now, size = 0, count = 0;

+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		if (data->registry_data.sclk_dpm_key_disabled)
@ -4717,7 +4721,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,

 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
@ -4727,7 +4731,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
@ -4737,7 +4741,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.gfx_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
@ -5112,6 +5116,8 @@ static int vega10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;

+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0],
 			title[1], title[2], title[3], title[4], title[5]);

--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@ -2141,6 +2141,8 @@ static int vega12_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 	int ret = 0;
 	int size = 0;

+	phm_get_sysfs_buf(&buf, &size);
+
 	ret = vega12_get_enabled_smc_features(hwmgr, &features_enabled);
 	PP_ASSERT_WITH_CODE(!ret,
 		"[EnableAllSmuFeatures] Failed to get enabled smc features!",
@ -2244,6 +2246,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int i, now, size = 0;
 	struct pp_clock_levels_with_latency clocks;

+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		PP_ASSERT_WITH_CODE(
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@ -3238,6 +3238,8 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 	int ret = 0;
 	int size = 0;

+	phm_get_sysfs_buf(&buf, &size);
+
 	ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled);
 	PP_ASSERT_WITH_CODE(!ret,
 			"[EnableAllSmuFeatures] Failed to get enabled smc features!",
@ -3364,6 +3366,8 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int ret = 0;
 	uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width;

+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		ret = vega20_get_current_clk_freq(hwmgr, PPCLK_GFXCLK, &now);
@ -3479,7 +3483,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	case OD_SCLK:
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 				od_table->GfxclkFmin);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@ -3489,7 +3493,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,

 	case OD_MCLK:
 		if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) {
-			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 				od_table->UclkFmax);
 		}
@ -3503,7 +3507,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) {
-			size = sysfs_emit(buf, "%s:\n", "OD_VDDC_CURVE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_VDDC_CURVE");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq1,
 				od_table->GfxclkVolt1 / VOLTAGE_SCALE);
@ -3518,7 +3522,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;

 	case OD_RANGE:
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");

 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
@ -4003,6 +4007,8 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;

+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
 			title[0], title[1], title[2], title[3], title[4], title[5],
 			title[6], title[7], title[8], title[9], title[10]);
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@ -1468,7 +1468,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 			dev_err(adev->dev, "Failed to disable smu features.\n");
 	}

-	if (adev->ip_versions[MP1_HWIP][0] >= IP_VERSION(11, 0, 0) &&
+	if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0) &&
 	    adev->gfx.rlc.funcs->stop)
 		adev->gfx.rlc.funcs->stop(adev);

@ -2534,13 +2534,15 @@ static int smu_get_power_profile_mode(void *handle, char *buf)
 	struct smu_context *smu = handle;
 	int ret = 0;

-	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled ||
+	    !smu->ppt_funcs->get_power_profile_mode)
 		return -EOPNOTSUPP;
+	if (!buf)
+		return -EINVAL;

 	mutex_lock(&smu->mutex);

-	if (smu->ppt_funcs->get_power_profile_mode)
-		ret = smu->ppt_funcs->get_power_profile_mode(smu, buf);
+	ret = smu->ppt_funcs->get_power_profile_mode(smu, buf);

 	mutex_unlock(&smu->mutex);

@ -2554,7 +2556,8 @@ static int smu_set_power_profile_mode(void *handle,
 	struct smu_context *smu = handle;
 	int ret = 0;

-	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled ||
+	    !smu->ppt_funcs->set_power_profile_mode)
 		return -EOPNOTSUPP;

 	mutex_lock(&smu->mutex);
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@ -64,7 +64,6 @@ static struct cmn2asic_msg_mapping yellow_carp_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(PowerDownVcn,                   PPSMC_MSG_PowerDownVcn,			1),
 	MSG_MAP(PowerUpVcn,                     PPSMC_MSG_PowerUpVcn,			1),
 	MSG_MAP(SetHardMinVcn,                  PPSMC_MSG_SetHardMinVcn,		1),
-	MSG_MAP(ActiveProcessNotify,            PPSMC_MSG_ActiveProcessNotify,		1),
 	MSG_MAP(PrepareMp1ForUnload,            PPSMC_MSG_PrepareMp1ForUnload,      1),
 	MSG_MAP(SetDriverDramAddrHigh,          PPSMC_MSG_SetDriverDramAddrHigh,	1),
 	MSG_MAP(SetDriverDramAddrLow,           PPSMC_MSG_SetDriverDramAddrLow,		1),
@ -135,14 +134,6 @@ static struct cmn2asic_mapping yellow_carp_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP_VALID(CUSTOM_DPM),
 	TAB_MAP_VALID(DPMCLOCKS),
 };
-
-static struct cmn2asic_mapping yellow_carp_workload_map[PP_SMC_POWER_PROFILE_COUNT] = {
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_FULLSCREEN3D,		WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO,		WORKLOAD_PPLIB_VIDEO_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR,			WORKLOAD_PPLIB_VR_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_COMPUTE_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
-};
 	
 static int yellow_carp_init_smc_tables(struct smu_context *smu)
 {
@ -543,81 +534,6 @@ static int yellow_carp_set_watermarks_table(struct smu_context *smu,
 	return 0;
 }

-static int yellow_carp_get_power_profile_mode(struct smu_context *smu,
-						char *buf)
-{
-	static const char *profile_name[] = {
-					"BOOTUP_DEFAULT",
-					"3D_FULL_SCREEN",
-					"POWER_SAVING",
-					"VIDEO",
-					"VR",
-					"COMPUTE",
-					"CUSTOM"};
-	uint32_t i, size = 0;
-	int16_t workload_type = 0;
-
-	if (!buf)
-		return -EINVAL;
-
-	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
-		/*
-		 * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT.
-		 * Not all profile modes are supported on yellow carp.
-		 */
-		workload_type = smu_cmn_to_asic_specific_index(smu,
-							       CMN2ASIC_MAPPING_WORKLOAD,
-							       i);
-
-		if (workload_type < 0)
-			continue;
-
-		size += sysfs_emit_at(buf, size, "%2d %14s%s\n",
-			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
-	}
-
-	return size;
-}
-
-static int yellow_carp_set_power_profile_mode(struct smu_context *smu,
-						long *input, uint32_t size)
-{
-	int workload_type, ret;
-	uint32_t profile_mode = input[size];
-
-	if (profile_mode > PP_SMC_POWER_PROFILE_CUSTOM) {
-		dev_err(smu->adev->dev, "Invalid power profile mode %d\n", profile_mode);
-		return -EINVAL;
-	}
-
-	if (profile_mode == PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT ||
-			profile_mode == PP_SMC_POWER_PROFILE_POWERSAVING)
-		return 0;
-
-	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
-	workload_type = smu_cmn_to_asic_specific_index(smu,
-						       CMN2ASIC_MAPPING_WORKLOAD,
-						       profile_mode);
-	if (workload_type < 0) {
-		dev_dbg(smu->adev->dev, "Unsupported power profile mode %d on YELLOWCARP\n",
-					profile_mode);
-		return -EINVAL;
-	}
-
-	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
-				    1 << workload_type,
-				    NULL);
-	if (ret) {
-		dev_err_once(smu->adev->dev, "Fail to set workload type %d\n",
-					workload_type);
-		return ret;
-	}
-
-	smu->power_profile_mode = profile_mode;
-
-	return 0;
-}
-
 static ssize_t yellow_carp_get_gpu_metrics(struct smu_context *smu,
 						void **table)
 {
@ -1238,8 +1154,6 @@ static const struct pptable_funcs yellow_carp_ppt_funcs = {
 	.read_sensor = yellow_carp_read_sensor,
 	.is_dpm_running = yellow_carp_is_dpm_running,
 	.set_watermarks_table = yellow_carp_set_watermarks_table,
-	.get_power_profile_mode = yellow_carp_get_power_profile_mode,
-	.set_power_profile_mode = yellow_carp_set_power_profile_mode,
 	.get_gpu_metrics = yellow_carp_get_gpu_metrics,
 	.get_enabled_mask = smu_cmn_get_enabled_32_bits_mask,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
@ -1261,6 +1175,5 @@ void yellow_carp_set_ppt_funcs(struct smu_context *smu)
 	smu->message_map = yellow_carp_message_map;
 	smu->feature_map = yellow_carp_feature_mask_map;
 	smu->table_map = yellow_carp_table_map;
-	smu->workload_map = yellow_carp_workload_map;
 	smu->is_apu = true;
 }
--- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
+++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
@ -167,9 +167,10 @@ static void lt9611uxc_hpd_work(struct work_struct *work)
 	struct lt9611uxc *lt9611uxc = container_of(work, struct lt9611uxc, work);
 	bool connected;

-	if (lt9611uxc->connector.dev)
-		drm_kms_helper_hotplug_event(lt9611uxc->connector.dev);
-	else {
+	if (lt9611uxc->connector.dev) {
+		if (lt9611uxc->connector.dev->mode_config.funcs)
+			drm_kms_helper_hotplug_event(lt9611uxc->connector.dev);
+	} else {

 		mutex_lock(&lt9611uxc->ocm_lock);
 		connected = lt9611uxc->hdmi_connected;
@ -339,6 +340,8 @@ static int lt9611uxc_connector_init(struct drm_bridge *bridge, struct lt9611uxc
 		return -ENODEV;
 	}

+	lt9611uxc->connector.polled = DRM_CONNECTOR_POLL_HPD;
+
 	drm_connector_helper_add(&lt9611uxc->connector,
 				 &lt9611uxc_bridge_connector_helper_funcs);
 	ret = drm_connector_init(bridge->dev, &lt9611uxc->connector,
--- a/drivers/gpu/drm/bridge/lvds-codec.c
+++ b/drivers/gpu/drm/bridge/lvds-codec.c
@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>

+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
 #include <drm/drm_panel.h>

@ -22,6 +23,7 @@ struct lvds_codec {
 	struct regulator *vcc;
 	struct gpio_desc *powerdown_gpio;
 	u32 connector_type;
+	unsigned int bus_format;
 };

 static inline struct lvds_codec *to_lvds_codec(struct drm_bridge *bridge)
@ -74,12 +76,50 @@ static const struct drm_bridge_funcs funcs = {
 	.disable = lvds_codec_disable,
 };

+#define MAX_INPUT_SEL_FORMATS 1
+static u32 *
+lvds_codec_atomic_get_input_bus_fmts(struct drm_bridge *bridge,
+				     struct drm_bridge_state *bridge_state,
+				     struct drm_crtc_state *crtc_state,
+				     struct drm_connector_state *conn_state,
+				     u32 output_fmt,
+				     unsigned int *num_input_fmts)
+{
+	struct lvds_codec *lvds_codec = to_lvds_codec(bridge);
+	u32 *input_fmts;
+
+	*num_input_fmts = 0;
+
+	input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts),
+			     GFP_KERNEL);
+	if (!input_fmts)
+		return NULL;
+
+	input_fmts[0] = lvds_codec->bus_format;
+	*num_input_fmts = MAX_INPUT_SEL_FORMATS;
+
+	return input_fmts;
+}
+
+static const struct drm_bridge_funcs funcs_decoder = {
+	.attach = lvds_codec_attach,
+	.enable = lvds_codec_enable,
+	.disable = lvds_codec_disable,
+	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
+	.atomic_reset = drm_atomic_helper_bridge_reset,
+	.atomic_get_input_bus_fmts = lvds_codec_atomic_get_input_bus_fmts,
+};
+
 static int lvds_codec_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *panel_node;
+	struct device_node *bus_node;
 	struct drm_panel *panel;
 	struct lvds_codec *lvds_codec;
+	const char *mapping;
+	int ret;

 	lvds_codec = devm_kzalloc(dev, sizeof(*lvds_codec), GFP_KERNEL);
 	if (!lvds_codec)
@ -119,13 +159,47 @@ static int lvds_codec_probe(struct platform_device *pdev)
 	if (IS_ERR(lvds_codec->panel_bridge))
 		return PTR_ERR(lvds_codec->panel_bridge);

+	lvds_codec->bridge.funcs = &funcs;
+
+	/*
+	 * Decoder input LVDS format is a property of the decoder chip or even
+	 * its strapping. Handle data-mapping the same way lvds-panel does. In
+	 * case data-mapping is not present, do nothing, since there are still
+	 * legacy bindings which do not specify this property.
+	 */
+	if (lvds_codec->connector_type != DRM_MODE_CONNECTOR_LVDS) {
+		bus_node = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0);
+		if (!bus_node) {
+			dev_dbg(dev, "bus DT node not found\n");
+			return -ENXIO;
+		}
+
+		ret = of_property_read_string(bus_node, "data-mapping",
+					      &mapping);
+		of_node_put(bus_node);
+		if (ret < 0) {
+			dev_warn(dev, "missing 'data-mapping' DT property\n");
+		} else {
+			if (!strcmp(mapping, "jeida-18")) {
+				lvds_codec->bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG;
+			} else if (!strcmp(mapping, "jeida-24")) {
+				lvds_codec->bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA;
+			} else if (!strcmp(mapping, "vesa-24")) {
+				lvds_codec->bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG;
+			} else {
+				dev_err(dev, "invalid 'data-mapping' DT property\n");
+				return -EINVAL;
+			}
+			lvds_codec->bridge.funcs = &funcs_decoder;
+		}
+	}
+
 	/*
 	 * The panel_bridge bridge is attached to the panel's of_node,
 	 * but we need a bridge attached to our of_node for our user
 	 * to look up.
 	 */
 	lvds_codec->bridge.of_node = dev->of_node;
-	lvds_codec->bridge.funcs = &funcs;
 	drm_bridge_add(&lvds_codec->bridge);

 	platform_set_drvdata(pdev, lvds_codec);
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@ -939,6 +939,40 @@ static void nwl_dsi_bridge_detach(struct drm_bridge *bridge)
 	drm_of_panel_bridge_remove(dsi->dev->of_node, 1, 0);
 }

+static u32 *nwl_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge,
+						 struct drm_bridge_state *bridge_state,
+						 struct drm_crtc_state *crtc_state,
+						 struct drm_connector_state *conn_state,
+						 u32 output_fmt,
+						 unsigned int *num_input_fmts)
+{
+	u32 *input_fmts, input_fmt;
+
+	*num_input_fmts = 0;
+
+	switch (output_fmt) {
+	/* If MEDIA_BUS_FMT_FIXED is tested, return default bus format */
+	case MEDIA_BUS_FMT_FIXED:
+		input_fmt = MEDIA_BUS_FMT_RGB888_1X24;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+	case MEDIA_BUS_FMT_RGB666_1X18:
+	case MEDIA_BUS_FMT_RGB565_1X16:
+		input_fmt = output_fmt;
+		break;
+	default:
+		return NULL;
+	}
+
+	input_fmts = kcalloc(1, sizeof(*input_fmts), GFP_KERNEL);
+	if (!input_fmts)
+		return NULL;
+	input_fmts[0] = input_fmt;
+	*num_input_fmts = 1;
+
+	return input_fmts;
+}
+
 static const struct drm_bridge_funcs nwl_dsi_bridge_funcs = {
 	.atomic_duplicate_state	= drm_atomic_helper_bridge_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_bridge_destroy_state,
@ -946,6 +980,7 @@ static const struct drm_bridge_funcs nwl_dsi_bridge_funcs = {
 	.atomic_check		= nwl_dsi_bridge_atomic_check,
 	.atomic_enable		= nwl_dsi_bridge_atomic_enable,
 	.atomic_disable		= nwl_dsi_bridge_atomic_disable,
+	.atomic_get_input_bus_fmts = nwl_bridge_atomic_get_input_bus_fmts,
 	.mode_set		= nwl_dsi_bridge_mode_set,
 	.mode_valid		= nwl_dsi_bridge_mode_valid,
 	.attach			= nwl_dsi_bridge_attach,
--- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
@ -288,6 +288,19 @@ err_dsi_attach:
 	return ret;
 }

+static void sn65dsi83_detach(struct drm_bridge *bridge)
+{
+	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
+
+	if (!ctx->dsi)
+		return;
+
+	mipi_dsi_detach(ctx->dsi);
+	mipi_dsi_device_unregister(ctx->dsi);
+	drm_bridge_remove(&ctx->bridge);
+	ctx->dsi = NULL;
+}
+
 static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge,
 					struct drm_bridge_state *old_bridge_state)
 {
@ -583,6 +596,7 @@ sn65dsi83_atomic_get_input_bus_fmts(struct drm_bridge *bridge,

 static const struct drm_bridge_funcs sn65dsi83_funcs = {
 	.attach			= sn65dsi83_attach,
+	.detach			= sn65dsi83_detach,
 	.atomic_pre_enable	= sn65dsi83_atomic_pre_enable,
 	.atomic_enable		= sn65dsi83_atomic_enable,
 	.atomic_disable		= sn65dsi83_atomic_disable,
@ -697,9 +711,6 @@ static int sn65dsi83_remove(struct i2c_client *client)
 {
 	struct sn65dsi83 *ctx = i2c_get_clientdata(client);

-	mipi_dsi_detach(ctx->dsi);
-	mipi_dsi_device_unregister(ctx->dsi);
-	drm_bridge_remove(&ctx->bridge);
 	of_node_put(ctx->host_node);

 	return 0;
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@ -625,6 +625,8 @@ int drm_connector_register_all(struct drm_device *dev)
 *
 * In contrast to the other drm_get_*_name functions this one here returns a
 * const pointer and hence is threadsafe.
+ *
+ * Returns: connector status string
 */
 const char *drm_get_connector_status_name(enum drm_connector_status status)
 {
@ -707,7 +709,7 @@ __drm_connector_put_safe(struct drm_connector *conn)
 * drm_connector_list_iter_next - return next connector
 * @iter: connector_list iterator
 *
- * Returns the next connector for @iter, or NULL when the list walk has
+ * Returns: the next connector for @iter, or NULL when the list walk has
 * completed.
 */
 struct drm_connector *
@ -780,6 +782,8 @@ static const struct drm_prop_enum_list drm_subpixel_enum_list[] = {
 *
 * Note you could abuse this and return something out of bounds, but that
 * would be a caller error.  No unscrubbed user data should make it here.
+ *
+ * Returns: string describing an enumerated subpixel property
 */
 const char *drm_get_subpixel_order_name(enum subpixel_order order)
 {
@ -809,6 +813,9 @@ static const struct drm_prop_enum_list drm_link_status_enum_list[] = {
 * Store the supported bus formats in display info structure.
 * See MEDIA_BUS_FMT_* definitions in include/uapi/linux/media-bus-format.h for
 * a full list of available formats.
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
 */
 int drm_display_info_set_bus_formats(struct drm_display_info *info,
 				     const u32 *formats,
@ -1326,6 +1333,8 @@ int drm_connector_create_standard_properties(struct drm_device *dev)
 * @dev: DRM device
 *
 * Called by a driver the first time a DVI-I connector is made.
+ *
+ * Returns: %0
 */
 int drm_mode_create_dvi_i_properties(struct drm_device *dev)
 {
@ -1397,6 +1406,8 @@ EXPORT_SYMBOL(drm_connector_attach_dp_subconnector_property);
 *	Game:
 *		Content type is game
 *
+ *	The meaning of each content type is defined in CTA-861-G table 15.
+ *
 *	Drivers can set up this property by calling
 *	drm_connector_attach_content_type_property(). Decoding to
 *	infoframe values is done through drm_hdmi_avi_infoframe_content_type().
@ -1407,6 +1418,8 @@ EXPORT_SYMBOL(drm_connector_attach_dp_subconnector_property);
 * @connector: connector to attach content type property on.
 *
 * Called by a driver the first time a HDMI connector is made.
+ *
+ * Returns: %0
 */
 int drm_connector_attach_content_type_property(struct drm_connector *connector)
 {
@ -1487,6 +1500,9 @@ EXPORT_SYMBOL(drm_connector_attach_tv_margin_properties);
 * creates the TV margin properties for a given device. No need to call this
 * function for an SDTV connector, it's already called from
 * drm_mode_create_tv_properties().
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
 */
 int drm_mode_create_tv_margin_properties(struct drm_device *dev)
 {
@ -1527,6 +1543,9 @@ EXPORT_SYMBOL(drm_mode_create_tv_margin_properties);
 * the TV specific connector properties for a given device.  Caller is
 * responsible for allocating a list of format names and passing them to
 * this routine.
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
 */
 int drm_mode_create_tv_properties(struct drm_device *dev,
 				  unsigned int num_modes,
@ -1622,6 +1641,8 @@ EXPORT_SYMBOL(drm_mode_create_tv_properties);
 * Atomic drivers should use drm_connector_attach_scaling_mode_property()
 * instead to correctly assign &drm_connector_state.scaling_mode
 * in the atomic state.
+ *
+ * Returns: %0
 */
 int drm_mode_create_scaling_mode_property(struct drm_device *dev)
 {
@ -1939,6 +1960,9 @@ EXPORT_SYMBOL(drm_mode_create_content_type_property);
 * @dev: DRM device
 *
 * Create the suggested x/y offset property for connectors.
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
 */
 int drm_mode_create_suggested_offset_properties(struct drm_device *dev)
 {
@ -2312,8 +2336,8 @@ int drm_connector_set_panel_orientation(
 EXPORT_SYMBOL(drm_connector_set_panel_orientation);

 /**
- * drm_connector_set_panel_orientation_with_quirk -
- *	set the connector's panel_orientation after checking for quirks
+ * drm_connector_set_panel_orientation_with_quirk - set the
+ *	connector's panel_orientation after checking for quirks
 * @connector: connector for which to init the panel-orientation property.
 * @panel_orientation: drm_panel_orientation value to set
 * @width: width in pixels of the panel, used for panel quirk detection
@ -2597,7 +2621,7 @@ struct drm_connector *drm_connector_find_by_fwnode(struct fwnode_handle *fwnode)

 /**
 * drm_connector_oob_hotplug_event - Report out-of-band hotplug event to connector
- * @connector: connector to report the event on
+ * @connector_fwnode: fwnode_handle to report the event on
 *
 * On some hardware a hotplug event notification may come from outside the display
 * driver / device. An example of this is some USB Type-C setups where the hardware
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@ -1340,31 +1340,15 @@ int drm_gem_fence_array_add_implicit(struct xarray *fence_array,
 				     struct drm_gem_object *obj,
 				     bool write)
 {
-	int ret;
-	struct dma_fence **fences;
-	unsigned int i, fence_count;
+	struct dma_resv_iter cursor;
+	struct dma_fence *fence;
+	int ret = 0;

-	if (!write) {
-		struct dma_fence *fence =
-			dma_resv_get_excl_unlocked(obj->resv);
-
-		return drm_gem_fence_array_add(fence_array, fence);
-	}
-
-	ret = dma_resv_get_fences(obj->resv, NULL,
-						&fence_count, &fences);
-	if (ret || !fence_count)
-		return ret;
-
-	for (i = 0; i < fence_count; i++) {
-		ret = drm_gem_fence_array_add(fence_array, fences[i]);
+	dma_resv_for_each_fence(&cursor, obj->resv, write, fence) {
+		ret = drm_gem_fence_array_add(fence_array, fence);
 		if (ret)
 			break;
 	}
-
-	for (; i < fence_count; i++)
-		dma_fence_put(fences[i]);
-	kfree(fences);
 	return ret;
 }
 EXPORT_SYMBOL(drm_gem_fence_array_add_implicit);
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@ -25,6 +25,7 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_device.h>
 #include <drm/drm_modeset_lock.h>
+#include <drm/drm_print.h>

 /**
 * DOC: kms locking
@ -77,6 +78,45 @@

 static DEFINE_WW_CLASS(crtc_ww_class);

+#if IS_ENABLED(CONFIG_DRM_DEBUG_MODESET_LOCK)
+static noinline depot_stack_handle_t __drm_stack_depot_save(void)
+{
+	unsigned long entries[8];
+	unsigned int n;
+
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+
+	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
+}
+
+static void __drm_stack_depot_print(depot_stack_handle_t stack_depot)
+{
+	struct drm_printer p = drm_debug_printer("drm_modeset_lock");
+	unsigned long *entries;
+	unsigned int nr_entries;
+	char *buf;
+
+	buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN);
+	if (!buf)
+		return;
+
+	nr_entries = stack_depot_fetch(stack_depot, &entries);
+	stack_trace_snprint(buf, PAGE_SIZE, entries, nr_entries, 2);
+
+	drm_printf(&p, "attempting to lock a contended lock without backoff:\n%s", buf);
+
+	kfree(buf);
+}
+#else /* CONFIG_DRM_DEBUG_MODESET_LOCK */
+static depot_stack_handle_t __drm_stack_depot_save(void)
+{
+	return 0;
+}
+static void __drm_stack_depot_print(depot_stack_handle_t stack_depot)
+{
+}
+#endif /* CONFIG_DRM_DEBUG_MODESET_LOCK */
+
 /**
 * drm_modeset_lock_all - take all modeset locks
 * @dev: DRM device
@ -225,7 +265,9 @@ EXPORT_SYMBOL(drm_modeset_acquire_fini);
 */
 void drm_modeset_drop_locks(struct drm_modeset_acquire_ctx *ctx)
 {
-	WARN_ON(ctx->contended);
+	if (WARN_ON(ctx->contended))
+		__drm_stack_depot_print(ctx->stack_depot);
+
 	while (!list_empty(&ctx->locked)) {
 		struct drm_modeset_lock *lock;

@ -243,7 +285,8 @@ static inline int modeset_lock(struct drm_modeset_lock *lock,
 {
 	int ret;

-	WARN_ON(ctx->contended);
+	if (WARN_ON(ctx->contended))
+		__drm_stack_depot_print(ctx->stack_depot);

 	if (ctx->trylock_only) {
 		lockdep_assert_held(&ctx->ww_ctx);
@ -274,6 +317,7 @@ static inline int modeset_lock(struct drm_modeset_lock *lock,
 		ret = 0;
 	} else if (ret == -EDEADLK) {
 		ctx->contended = lock;
+		ctx->stack_depot = __drm_stack_depot_save();
 	}

 	return ret;
@ -296,6 +340,7 @@ int drm_modeset_backoff(struct drm_modeset_acquire_ctx *ctx)
 	struct drm_modeset_lock *contended = ctx->contended;

 	ctx->contended = NULL;
+	ctx->stack_depot = 0;

 	if (WARN_ON(!contended))
 		return 0;
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@ -123,7 +123,6 @@ static int drm_plane_helper_check_update(struct drm_plane *plane,
 		.crtc_w = drm_rect_width(dst),
 		.crtc_h = drm_rect_height(dst),
 		.rotation = rotation,
-		.visible = *visible,
 	};
 	struct drm_crtc_state crtc_state = {
 		.crtc = crtc,
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@ -722,11 +722,13 @@ int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	if (obj->funcs && obj->funcs->mmap) {
 		vma->vm_ops = obj->funcs->vm_ops;

-		ret = obj->funcs->mmap(obj, vma);
-		if (ret)
-			return ret;
-		vma->vm_private_data = obj;
 		drm_gem_object_get(obj);
+		ret = obj->funcs->mmap(obj, vma);
+		if (ret) {
+			drm_gem_object_put(obj);
+			return ret;
+		}
+		vma->vm_private_data = obj;
 		return 0;
 	}

--- a/drivers/gpu/drm/i915/display/g4x_hdmi.c
+++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c
@ -584,6 +584,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 		else
 			intel_encoder->enable = g4x_enable_hdmi;
 	}
+	intel_encoder->shutdown = intel_hdmi_encoder_shutdown;

 	intel_encoder->type = INTEL_OUTPUT_HDMI;
 	intel_encoder->power_domain = intel_port_to_power_domain(port);
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@ -1707,6 +1707,39 @@ static void sanitize_aux_ch(struct intel_bios_encoder_data *devdata,
 	child->aux_channel = 0;
 }

+static u8 dvo_port_type(u8 dvo_port)
+{
+	switch (dvo_port) {
+	case DVO_PORT_HDMIA:
+	case DVO_PORT_HDMIB:
+	case DVO_PORT_HDMIC:
+	case DVO_PORT_HDMID:
+	case DVO_PORT_HDMIE:
+	case DVO_PORT_HDMIF:
+	case DVO_PORT_HDMIG:
+	case DVO_PORT_HDMIH:
+	case DVO_PORT_HDMII:
+		return DVO_PORT_HDMIA;
+	case DVO_PORT_DPA:
+	case DVO_PORT_DPB:
+	case DVO_PORT_DPC:
+	case DVO_PORT_DPD:
+	case DVO_PORT_DPE:
+	case DVO_PORT_DPF:
+	case DVO_PORT_DPG:
+	case DVO_PORT_DPH:
+	case DVO_PORT_DPI:
+		return DVO_PORT_DPA;
+	case DVO_PORT_MIPIA:
+	case DVO_PORT_MIPIB:
+	case DVO_PORT_MIPIC:
+	case DVO_PORT_MIPID:
+		return DVO_PORT_MIPIA;
+	default:
+		return dvo_port;
+	}
+}
+
 static enum port __dvo_port_to_port(int n_ports, int n_dvo,
 				    const int port_mapping[][3], u8 dvo_port)
 {
@ -1930,50 +1963,6 @@ static int _intel_bios_max_tmds_clock(const struct intel_bios_encoder_data *devd
 	}
 }

-static enum port get_edp_port(struct drm_i915_private *i915)
-{
-	const struct intel_bios_encoder_data *devdata;
-	enum port port;
-
-	for_each_port(port) {
-		devdata = i915->vbt.ports[port];
-
-		if (devdata && intel_bios_encoder_supports_edp(devdata))
-			return port;
-	}
-
-	return PORT_NONE;
-}
-
-/*
- * FIXME: The power sequencer and backlight code currently do not support more
- * than one set registers, at least not on anything other than VLV/CHV. It will
- * clobber the registers. As a temporary workaround, gracefully prevent more
- * than one eDP from being registered.
- */
-static void sanitize_dual_edp(struct intel_bios_encoder_data *devdata,
-			      enum port port)
-{
-	struct drm_i915_private *i915 = devdata->i915;
-	struct child_device_config *child = &devdata->child;
-	enum port p;
-
-	/* CHV might not clobber PPS registers. */
-	if (IS_CHERRYVIEW(i915))
-		return;
-
-	p = get_edp_port(i915);
-	if (p == PORT_NONE)
-		return;
-
-	drm_dbg_kms(&i915->drm, "both ports %c and %c configured as eDP, "
-		    "disabling port %c eDP\n", port_name(p), port_name(port),
-		    port_name(port));
-
-	child->device_type &= ~DEVICE_TYPE_DISPLAYPORT_OUTPUT;
-	child->device_type &= ~DEVICE_TYPE_INTERNAL_CONNECTOR;
-}
-
 static bool is_port_valid(struct drm_i915_private *i915, enum port port)
 {
 	/*
@ -2031,9 +2020,6 @@ static void parse_ddi_port(struct drm_i915_private *i915,
 		    supports_typec_usb, supports_tbt,
 		    devdata->dsc != NULL);

-	if (is_edp)
-		sanitize_dual_edp(devdata, port);
-
 	if (is_dvi)
 		sanitize_ddc_pin(devdata, port);

@ -2670,8 +2656,25 @@ bool intel_bios_is_port_edp(struct drm_i915_private *i915, enum port port)
 	return false;
 }

-static bool child_dev_is_dp_dual_mode(const struct child_device_config *child,
-				      enum port port)
+static bool child_dev_is_dp_dual_mode(const struct child_device_config *child)
+{
+	if ((child->device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) !=
+	    (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS))
+		return false;
+
+	if (dvo_port_type(child->dvo_port) == DVO_PORT_DPA)
+		return true;
+
+	/* Only accept a HDMI dvo_port as DP++ if it has an AUX channel */
+	if (dvo_port_type(child->dvo_port) == DVO_PORT_HDMIA &&
+	    child->aux_channel != 0)
+		return true;
+
+	return false;
+}
+
+bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *i915,
+				     enum port port)
 {
 	static const struct {
 		u16 dp, hdmi;
@ -2686,32 +2689,23 @@ static bool child_dev_is_dp_dual_mode(const struct child_device_config *child,
 		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
 		[PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, },
 	};
+	const struct intel_bios_encoder_data *devdata;
+
+	if (HAS_DDI(i915)) {
+		const struct intel_bios_encoder_data *devdata;
+
+		devdata = intel_bios_encoder_data_lookup(i915, port);
+
+		return devdata && child_dev_is_dp_dual_mode(&devdata->child);
+	}

 	if (port == PORT_A || port >= ARRAY_SIZE(port_mapping))
 		return false;

-	if ((child->device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) !=
-	    (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS))
-		return false;
-
-	if (child->dvo_port == port_mapping[port].dp)
-		return true;
-
-	/* Only accept a HDMI dvo_port as DP++ if it has an AUX channel */
-	if (child->dvo_port == port_mapping[port].hdmi &&
-	    child->aux_channel != 0)
-		return true;
-
-	return false;
-}
-
-bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *i915,
-				     enum port port)
-{
-	const struct intel_bios_encoder_data *devdata;
-
 	list_for_each_entry(devdata, &i915->vbt.display_devices, node) {
-		if (child_dev_is_dp_dual_mode(&devdata->child, port))
+		if ((devdata->child.dvo_port == port_mapping[port].dp ||
+		     devdata->child.dvo_port == port_mapping[port].hdmi) &&
+		    child_dev_is_dp_dual_mode(&devdata->child))
 			return true;
 	}

--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@ -2885,7 +2885,7 @@ u32 intel_read_rawclk(struct drm_i915_private *dev_priv)
 	return freq;
 }

-static struct intel_cdclk_funcs tgl_cdclk_funcs = {
+static const struct intel_cdclk_funcs tgl_cdclk_funcs = {
 	.get_cdclk = bxt_get_cdclk,
 	.set_cdclk = bxt_set_cdclk,
 	.bw_calc_min_cdclk = skl_bw_calc_min_cdclk,
@ -2893,7 +2893,7 @@ static struct intel_cdclk_funcs tgl_cdclk_funcs = {
 	.calc_voltage_level = tgl_calc_voltage_level,
 };

-static struct intel_cdclk_funcs ehl_cdclk_funcs = {
+static const struct intel_cdclk_funcs ehl_cdclk_funcs = {
 	.get_cdclk = bxt_get_cdclk,
 	.set_cdclk = bxt_set_cdclk,
 	.bw_calc_min_cdclk = skl_bw_calc_min_cdclk,
@ -2901,7 +2901,7 @@ static struct intel_cdclk_funcs ehl_cdclk_funcs = {
 	.calc_voltage_level = ehl_calc_voltage_level,
 };

-static struct intel_cdclk_funcs icl_cdclk_funcs = {
+static const struct intel_cdclk_funcs icl_cdclk_funcs = {
 	.get_cdclk = bxt_get_cdclk,
 	.set_cdclk = bxt_set_cdclk,
 	.bw_calc_min_cdclk = skl_bw_calc_min_cdclk,
@ -2909,7 +2909,7 @@ static struct intel_cdclk_funcs icl_cdclk_funcs = {
 	.calc_voltage_level = icl_calc_voltage_level,
 };

-static struct intel_cdclk_funcs bxt_cdclk_funcs = {
+static const struct intel_cdclk_funcs bxt_cdclk_funcs = {
 	.get_cdclk = bxt_get_cdclk,
 	.set_cdclk = bxt_set_cdclk,
 	.bw_calc_min_cdclk = skl_bw_calc_min_cdclk,
@ -2917,54 +2917,54 @@ static struct intel_cdclk_funcs bxt_cdclk_funcs = {
 	.calc_voltage_level = bxt_calc_voltage_level,
 };

-static struct intel_cdclk_funcs skl_cdclk_funcs = {
+static const struct intel_cdclk_funcs skl_cdclk_funcs = {
 	.get_cdclk = skl_get_cdclk,
 	.set_cdclk = skl_set_cdclk,
 	.bw_calc_min_cdclk = skl_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = skl_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs bdw_cdclk_funcs = {
+static const struct intel_cdclk_funcs bdw_cdclk_funcs = {
 	.get_cdclk = bdw_get_cdclk,
 	.set_cdclk = bdw_set_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = bdw_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs chv_cdclk_funcs = {
+static const struct intel_cdclk_funcs chv_cdclk_funcs = {
 	.get_cdclk = vlv_get_cdclk,
 	.set_cdclk = chv_set_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = vlv_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs vlv_cdclk_funcs = {
+static const struct intel_cdclk_funcs vlv_cdclk_funcs = {
 	.get_cdclk = vlv_get_cdclk,
 	.set_cdclk = vlv_set_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = vlv_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs hsw_cdclk_funcs = {
+static const struct intel_cdclk_funcs hsw_cdclk_funcs = {
 	.get_cdclk = hsw_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

 /* SNB, IVB, 965G, 945G */
-static struct intel_cdclk_funcs fixed_400mhz_cdclk_funcs = {
+static const struct intel_cdclk_funcs fixed_400mhz_cdclk_funcs = {
 	.get_cdclk = fixed_400mhz_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs ilk_cdclk_funcs = {
+static const struct intel_cdclk_funcs ilk_cdclk_funcs = {
 	.get_cdclk = fixed_450mhz_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs gm45_cdclk_funcs = {
+static const struct intel_cdclk_funcs gm45_cdclk_funcs = {
 	.get_cdclk = gm45_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
@ -2972,7 +2972,7 @@ static struct intel_cdclk_funcs gm45_cdclk_funcs = {

 /* G45 uses G33 */

-static struct intel_cdclk_funcs i965gm_cdclk_funcs = {
+static const struct intel_cdclk_funcs i965gm_cdclk_funcs = {
 	.get_cdclk = i965gm_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
@ -2980,19 +2980,19 @@ static struct intel_cdclk_funcs i965gm_cdclk_funcs = {

 /* i965G uses fixed 400 */

-static struct intel_cdclk_funcs pnv_cdclk_funcs = {
+static const struct intel_cdclk_funcs pnv_cdclk_funcs = {
 	.get_cdclk = pnv_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs g33_cdclk_funcs = {
+static const struct intel_cdclk_funcs g33_cdclk_funcs = {
 	.get_cdclk = g33_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs i945gm_cdclk_funcs = {
+static const struct intel_cdclk_funcs i945gm_cdclk_funcs = {
 	.get_cdclk = i945gm_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
@ -3000,37 +3000,37 @@ static struct intel_cdclk_funcs i945gm_cdclk_funcs = {

 /* i945G uses fixed 400 */

-static struct intel_cdclk_funcs i915gm_cdclk_funcs = {
+static const struct intel_cdclk_funcs i915gm_cdclk_funcs = {
 	.get_cdclk = i915gm_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs i915g_cdclk_funcs = {
+static const struct intel_cdclk_funcs i915g_cdclk_funcs = {
 	.get_cdclk = fixed_333mhz_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs i865g_cdclk_funcs = {
+static const struct intel_cdclk_funcs i865g_cdclk_funcs = {
 	.get_cdclk = fixed_266mhz_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs i85x_cdclk_funcs = {
+static const struct intel_cdclk_funcs i85x_cdclk_funcs = {
 	.get_cdclk = i85x_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs i845g_cdclk_funcs = {
+static const struct intel_cdclk_funcs i845g_cdclk_funcs = {
 	.get_cdclk = fixed_200mhz_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
 };

-static struct intel_cdclk_funcs i830_cdclk_funcs = {
+static const struct intel_cdclk_funcs i830_cdclk_funcs = {
 	.get_cdclk = fixed_133mhz_get_cdclk,
 	.bw_calc_min_cdclk = intel_bw_calc_min_cdclk,
 	.modeset_calc_cdclk = fixed_modeset_calc_cdclk,
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@ -4361,6 +4361,7 @@ static void intel_ddi_encoder_shutdown(struct intel_encoder *encoder)
 	enum phy phy = intel_port_to_phy(i915, encoder->port);

 	intel_dp_encoder_shutdown(encoder);
+	intel_hdmi_encoder_shutdown(encoder);

 	if (!intel_phy_is_tc(i915, phy))
 		return;
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@ -848,9 +848,16 @@ unsigned int intel_remapped_info_size(const struct intel_remapped_info *rem_info
 	int i;

 	for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) {
+		unsigned int plane_size;
+
+		plane_size = rem_info->plane[i].dst_stride * rem_info->plane[i].height;
+		if (plane_size == 0)
+			continue;
+
 		if (rem_info->plane_alignment)
 			size = ALIGN(size, rem_info->plane_alignment);
-		size += rem_info->plane[i].dst_stride * rem_info->plane[i].height;
+
+		size += plane_size;
 	}

 	return size;
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@ -120,6 +120,12 @@ bool intel_dp_is_uhbr(const struct intel_crtc_state *crtc_state)
 	return crtc_state->port_clock >= 1000000;
 }

+static void intel_dp_set_default_sink_rates(struct intel_dp *intel_dp)
+{
+	intel_dp->sink_rates[0] = 162000;
+	intel_dp->num_sink_rates = 1;
+}
+
 /* update sink rates from dpcd */
 static void intel_dp_set_sink_rates(struct intel_dp *intel_dp)
 {
@ -281,7 +287,7 @@ intel_dp_max_data_rate(int max_link_rate, int max_lanes)
 		 */
 		int max_link_rate_kbps = max_link_rate * 10;

-		max_link_rate_kbps = DIV_ROUND_CLOSEST_ULL(max_link_rate_kbps * 9671, 10000);
+		max_link_rate_kbps = DIV_ROUND_CLOSEST_ULL(mul_u32_u32(max_link_rate_kbps, 9671), 10000);
 		max_link_rate = max_link_rate_kbps / 8;
 	}

@ -1858,6 +1864,12 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp,
 	intel_dp->lane_count = lane_count;
 }

+static void intel_dp_reset_max_link_params(struct intel_dp *intel_dp)
+{
+	intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp);
+	intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp);
+}
+
 /* Enable backlight PWM and backlight PP control. */
 void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state,
 			    const struct drm_connector_state *conn_state)
@ -2017,8 +2029,7 @@ void intel_dp_sync_state(struct intel_encoder *encoder,
 	if (intel_dp->dpcd[DP_DPCD_REV] == 0)
 		intel_dp_get_dpcd(intel_dp);

-	intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp);
-	intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp);
+	intel_dp_reset_max_link_params(intel_dp);
 }

 bool intel_dp_initial_fastset_check(struct intel_encoder *encoder,
@ -2556,6 +2567,9 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	 */
 	intel_psr_init_dpcd(intel_dp);

+	/* Clear the default sink rates */
+	intel_dp->num_sink_rates = 0;
+
 	/* Read the eDP 1.4+ supported link rates. */
 	if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
 		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
@ -2591,6 +2605,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 		intel_dp_set_sink_rates(intel_dp);

 	intel_dp_set_common_rates(intel_dp);
+	intel_dp_reset_max_link_params(intel_dp);

 	/* Read the eDP DSC DPCD registers */
 	if (DISPLAY_VER(dev_priv) >= 10)
@ -4332,12 +4347,7 @@ intel_dp_detect(struct drm_connector *connector,
 	 * supports link training fallback params.
 	 */
 	if (intel_dp->reset_link_params || intel_dp->is_mst) {
-		/* Initial max link lane count */
-		intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp);
-
-		/* Initial max link rate */
-		intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp);
-
+		intel_dp_reset_max_link_params(intel_dp);
 		intel_dp->reset_link_params = false;
 	}

@ -5003,6 +5013,9 @@ intel_dp_init_connector(struct intel_digital_port *dig_port,
 	}

 	intel_dp_set_source_rates(intel_dp);
+	intel_dp_set_default_sink_rates(intel_dp);
+	intel_dp_set_common_rates(intel_dp);
+	intel_dp_reset_max_link_params(intel_dp);

 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		intel_dp->pps.active_pipe = vlv_active_pipe(intel_dp);
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@ -378,8 +378,8 @@ static void intel_fb_plane_dims(const struct intel_framebuffer *fb, int color_pl
 	intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, &fb->base, main_plane);
 	intel_fb_plane_get_subsampling(&hsub, &vsub, &fb->base, color_plane);

-	*w = main_width / main_hsub / hsub;
-	*h = main_height / main_vsub / vsub;
+	*w = DIV_ROUND_UP(main_width, main_hsub * hsub);
+	*h = DIV_ROUND_UP(main_height, main_vsub * vsub);
 }

 static u32 intel_adjust_tile_offset(int *x, int *y,
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@ -1246,12 +1246,13 @@ static void hsw_set_infoframes(struct intel_encoder *encoder,
 void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable)
 {
 	struct drm_i915_private *dev_priv = intel_hdmi_to_i915(hdmi);
-	struct i2c_adapter *adapter =
-		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
+	struct i2c_adapter *adapter;

 	if (hdmi->dp_dual_mode.type < DRM_DP_DUAL_MODE_TYPE2_DVI)
 		return;

+	adapter = intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
+
 	drm_dbg_kms(&dev_priv->drm, "%s DP dual mode adaptor TMDS output\n",
 		    enable ? "Enabling" : "Disabling");

@ -2258,6 +2259,17 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	return 0;
 }

+void intel_hdmi_encoder_shutdown(struct intel_encoder *encoder)
+{
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+
+	/*
+	 * Give a hand to buggy BIOSen which forget to turn
+	 * the TMDS output buffers back on after a reboot.
+	 */
+	intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
+}
+
 static void
 intel_hdmi_unset_edid(struct drm_connector *connector)
 {
--- a/drivers/gpu/drm/i915/display/intel_hdmi.h
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.h
@ -28,6 +28,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port,
 int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state);
+void intel_hdmi_encoder_shutdown(struct intel_encoder *encoder);
 bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
 				       struct drm_connector *connector,
 				       bool high_tmds_clock_ratio,
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@ -9,6 +9,8 @@
 #include <linux/dma-resv.h>
 #include <linux/module.h>

+#include <asm/smp.h>
+
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@ -1396,6 +1396,9 @@ remap_pages(struct drm_i915_gem_object *obj,
 {
 	unsigned int row;

+	if (!width || !height)
+		return sg;
+
 	if (alignment_pad) {
 		st->nents++;

--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@ -2373,6 +2373,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce)
 	unsigned long flags;
 	bool disabled;

+	lockdep_assert_held(&guc->submission_state.lock);
 	GEM_BUG_ON(!intel_gt_pm_is_awake(gt));
 	GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id));
 	GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id));
@ -2388,7 +2389,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce)
 	}
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 	if (unlikely(disabled)) {
-		release_guc_id(guc, ce);
+		__release_guc_id(guc, ce);
 		__guc_context_destroy(ce);
 		return;
 	}
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@ -1537,38 +1537,14 @@ i915_request_await_object(struct i915_request *to,
 			  struct drm_i915_gem_object *obj,
 			  bool write)
 {
-	struct dma_fence *excl;
+	struct dma_resv_iter cursor;
+	struct dma_fence *fence;
 	int ret = 0;

-	if (write) {
-		struct dma_fence **shared;
-		unsigned int count, i;
-
-		ret = dma_resv_get_fences(obj->base.resv, &excl, &count,
-					  &shared);
+	dma_resv_for_each_fence(&cursor, obj->base.resv, write, fence) {
+		ret = i915_request_await_dma_fence(to, fence);
 		if (ret)
-			return ret;
-
-		for (i = 0; i < count; i++) {
-			ret = i915_request_await_dma_fence(to, shared[i]);
-			if (ret)
-				break;
-
-			dma_fence_put(shared[i]);
-		}
-
-		for (; i < count; i++)
-			dma_fence_put(shared[i]);
-		kfree(shared);
-	} else {
-		excl = dma_resv_get_excl_unlocked(obj->base.resv);
-	}
-
-	if (excl) {
-		if (ret == 0)
-			ret = i915_request_await_dma_fence(to, excl);
-
-		dma_fence_put(excl);
+			break;
 	}

 	return ret;
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@ -81,7 +81,6 @@ static void imx_drm_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_plane_state *old_plane_state, *new_plane_state;
 	bool plane_disabling = false;
 	int i;
-	bool fence_cookie = dma_fence_begin_signalling();

 	drm_atomic_helper_commit_modeset_disables(dev, state);

@ -112,7 +111,6 @@ static void imx_drm_atomic_commit_tail(struct drm_atomic_state *state)
 	}

 	drm_atomic_helper_commit_hw_done(state);
-	dma_fence_end_signalling(fence_cookie);
 }

 static const struct drm_mode_config_helper_funcs imx_drm_mode_config_helpers = {
--- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
@ -88,7 +88,7 @@ static void mxsfb_set_formats(struct mxsfb_drm_private *mxsfb,
 		ctrl |= CTRL_BUS_WIDTH_24;
 		break;
 	default:
-		dev_err(drm->dev, "Unknown media bus format %d\n", bus_format);
+		dev_err(drm->dev, "Unknown media bus format 0x%x\n", bus_format);
 		break;
 	}

@ -362,6 +362,12 @@ static void mxsfb_crtc_atomic_enable(struct drm_crtc *crtc,
 			drm_atomic_get_new_bridge_state(state,
 							mxsfb->bridge);
 		bus_format = bridge_state->input_bus_cfg.format;
+		if (bus_format == MEDIA_BUS_FMT_FIXED) {
+			dev_warn_once(drm->dev,
+				      "Bridge does not provide bus format, assuming MEDIA_BUS_FMT_RGB888_1X24.\n"
+				      "Please fix bridge driver by handling atomic_get_input_bus_fmts.\n");
+			bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+		}
 	}

 	/* If there is no bridge, use bus format from connector */
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@ -1249,7 +1249,6 @@ nouveau_ttm_tt_populate(struct ttm_device *bdev,
 {
 	struct ttm_tt *ttm_dma = (void *)ttm;
 	struct nouveau_drm *drm;
-	struct device *dev;
 	bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL);

 	if (ttm_tt_is_populated(ttm))
@ -1262,7 +1261,6 @@ nouveau_ttm_tt_populate(struct ttm_device *bdev,
 	}

 	drm = nouveau_bdev(bdev);
-	dev = drm->dev->dev;

 	return ttm_pool_alloc(&drm->ttm.bdev.pool, ttm, ctx);
 }
@ -1272,7 +1270,6 @@ nouveau_ttm_tt_unpopulate(struct ttm_device *bdev,
 			  struct ttm_tt *ttm)
 {
 	struct nouveau_drm *drm;
-	struct device *dev;
 	bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL);

 	if (slave)
@ -1281,7 +1278,6 @@ nouveau_ttm_tt_unpopulate(struct ttm_device *bdev,
 	nouveau_ttm_tt_unbind(bdev, ttm);

 	drm = nouveau_bdev(bdev);
-	dev = drm->dev->dev;

 	return ttm_pool_free(&drm->ttm.bdev.pool, ttm);
 }
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@ -562,6 +562,7 @@ nouveau_drm_device_init(struct drm_device *dev)
 		nvkm_dbgopt(nouveau_debug, "DRM");

 	INIT_LIST_HEAD(&drm->clients);
+	mutex_init(&drm->clients_lock);
 	spin_lock_init(&drm->tile.lock);

 	/* workaround an odd issue on nvc1 by disabling the device's
@ -632,6 +633,7 @@ fail_alloc:
 static void
 nouveau_drm_device_fini(struct drm_device *dev)
 {
+	struct nouveau_cli *cli, *temp_cli;
 	struct nouveau_drm *drm = nouveau_drm(dev);

 	if (nouveau_pmops_runtime()) {
@ -656,9 +658,28 @@ nouveau_drm_device_fini(struct drm_device *dev)
 	nouveau_ttm_fini(drm);
 	nouveau_vga_fini(drm);

+	/*
+	 * There may be existing clients from as-yet unclosed files. For now,
+	 * clean them up here rather than deferring until the file is closed,
+	 * but this likely not correct if we want to support hot-unplugging
+	 * properly.
+	 */
+	mutex_lock(&drm->clients_lock);
+	list_for_each_entry_safe(cli, temp_cli, &drm->clients, head) {
+		list_del(&cli->head);
+		mutex_lock(&cli->mutex);
+		if (cli->abi16)
+			nouveau_abi16_fini(cli->abi16);
+		mutex_unlock(&cli->mutex);
+		nouveau_cli_fini(cli);
+		kfree(cli);
+	}
+	mutex_unlock(&drm->clients_lock);
+
 	nouveau_cli_fini(&drm->client);
 	nouveau_cli_fini(&drm->master);
 	nvif_parent_dtor(&drm->parent);
+	mutex_destroy(&drm->clients_lock);
 	kfree(drm);
 }

@ -796,7 +817,7 @@ nouveau_drm_device_remove(struct drm_device *dev)
 	struct nvkm_client *client;
 	struct nvkm_device *device;

-	drm_dev_unregister(dev);
+	drm_dev_unplug(dev);

 	client = nvxx_client(&drm->client.base);
 	device = nvkm_device_find(client->device);
@ -1090,9 +1111,9 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)

 	fpriv->driver_priv = cli;

-	mutex_lock(&drm->client.mutex);
+	mutex_lock(&drm->clients_lock);
 	list_add(&cli->head, &drm->clients);
-	mutex_unlock(&drm->client.mutex);
+	mutex_unlock(&drm->clients_lock);

 done:
 	if (ret && cli) {
@ -1110,6 +1131,16 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv)
 {
 	struct nouveau_cli *cli = nouveau_cli(fpriv);
 	struct nouveau_drm *drm = nouveau_drm(dev);
+	int dev_index;
+
+	/*
+	 * The device is gone, and as it currently stands all clients are
+	 * cleaned up in the removal codepath. In the future this may change
+	 * so that we can support hot-unplugging, but for now we immediately
+	 * return to avoid a double-free situation.
+	 */
+	if (!drm_dev_enter(dev, &dev_index))
+		return;

 	pm_runtime_get_sync(dev->dev);

@ -1118,14 +1149,15 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv)
 		nouveau_abi16_fini(cli->abi16);
 	mutex_unlock(&cli->mutex);

-	mutex_lock(&drm->client.mutex);
+	mutex_lock(&drm->clients_lock);
 	list_del(&cli->head);
-	mutex_unlock(&drm->client.mutex);
+	mutex_unlock(&drm->clients_lock);

 	nouveau_cli_fini(cli);
 	kfree(cli);
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
+	drm_dev_exit(dev_index);
 }

 static const struct drm_ioctl_desc
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@ -139,6 +139,11 @@ struct nouveau_drm {

 	struct list_head clients;

+	/**
+	 * @clients_lock: Protects access to the @clients list of &struct nouveau_cli.
+	 */
+	struct mutex clients_lock;
+
 	u8 old_pm_cap;

 	struct {
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@ -56,7 +56,7 @@ static vm_fault_t nouveau_ttm_fault(struct vm_fault *vmf)

 	nouveau_bo_del_io_reserve_lru(bo);
 	prot = vm_get_page_prot(vma->vm_flags);
-	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1);
+	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
 	nouveau_bo_add_io_reserve_lru(bo);
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
@ -337,7 +337,7 @@ nouveau_gem_set_domain(struct drm_gem_object *gem, uint32_t read_domains,
 	struct ttm_buffer_object *bo = &nvbo->bo;
 	uint32_t domains = valid_domains & nvbo->valid_domains &
 		(write_domains ? write_domains : read_domains);
-	uint32_t pref_domains = 0;;
+	uint32_t pref_domains = 0;

 	if (!domains)
 		return -EINVAL;
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@ -162,10 +162,14 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	 */

 	mm = get_task_mm(current);
+	if (!mm) {
+		return -EINVAL;
+	}
 	mmap_read_lock(mm);

 	if (!cli->svm.svmm) {
 		mmap_read_unlock(mm);
+		mmput(mm);
 		return -EINVAL;
 	}

--- a/Show More
+++ b/Show More